diff --git a/notebooks/cognee_demo.ipynb b/notebooks/cognee_demo.ipynb
index 8983ccb09..46c355321 100644
--- a/notebooks/cognee_demo.ipynb
+++ b/notebooks/cognee_demo.ipynb
@@ -68,30 +68,6 @@
     "\n"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "8aba58c24daec519",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2025-06-30T11:38:36.328621Z",
-     "start_time": "2025-06-30T11:38:36.068313Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "0.2.4-local\n"
-     ]
-    }
-   ],
-   "source": [
-    "import cognee\n",
-    "print(cognee.__version__)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "074f0ea8-c659-4736-be26-be4b0e5ac665",
@@ -110,7 +86,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "df16431d0f48b006",
    "metadata": {
     "ExecuteTime": {
@@ -419,7 +395,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 1,
    "id": "9f1a1dbd",
    "metadata": {
     "ExecuteTime": {
@@ -433,9 +409,32 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "\u001b[2m2025-08-27T13:01:17.533854\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted Kuzu database files at /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases/cognee_graph_kuzu\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:36:22.969905\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted old log file: /Users/daulet/Desktop/dev/cognee-claude/logs/2025-10-07_21-15-58.log\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:01:18.755266\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase deleted successfully.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
+      "\u001b[2m2025-10-07T20:36:23.577073\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLogging initialized           \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m \u001b[36mcognee_version\u001b[0m=\u001b[35m0.3.5-local\u001b[0m \u001b[36mdatabase_path\u001b[0m=\u001b[35m/Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m \u001b[36mgraph_database_name\u001b[0m=\u001b[35m\u001b[0m \u001b[36mos_info\u001b[0m=\u001b[35m'Darwin 24.5.0 (Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:43 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8132)'\u001b[0m \u001b[36mpython_version\u001b[0m=\u001b[35m3.10.11\u001b[0m \u001b[36mrelational_config\u001b[0m=\u001b[35mcognee_db\u001b[0m \u001b[36mstructlog_version\u001b[0m=\u001b[35m25.4.0\u001b[0m \u001b[36mvector_config\u001b[0m=\u001b[35mlancedb\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:36:23.577696\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase storage: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "/Users/daulet/Desktop/dev/cognee-claude/.venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:36:28.324602\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mJSON extension already loaded or unavailable: Binder exception: Extension: JSON is already loaded. You can check loaded extensions by `CALL SHOW_LOADED_EXTENSIONS() RETURN *`.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:36:28.362499\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted Kuzu database files at /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases/cognee_graph_kuzu\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:36:30.889776\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase deleted successfully.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[1mStorage manager absolute path: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_cache\u001b[0m\n",
+      "\n",
+      "\u001b[1mDeleting cache...             \u001b[0m\n",
+      "\n",
+      "\u001b[1m✓ Cache deleted successfully! \u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.3.5-local\n"
      ]
     }
    ],
@@ -445,7 +444,8 @@
     "import cognee\n",
     "\n",
     "await cognee.prune.prune_data()\n",
-    "await cognee.prune.prune_system(metadata=True)"
+    "await cognee.prune.prune_system(metadata=True)\n",
+    "print(cognee.__version__)"
    ]
   },
   {
@@ -458,7 +458,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "id": "904df61ba484a8e5",
    "metadata": {
     "ExecuteTime": {
@@ -466,7 +466,117 @@
      "start_time": "2025-06-30T11:39:32.388973Z"
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "User 17d4a6b1-da2b-46b8-a607-06969eda0881 has registered.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1mEmbeddingRateLimiter initialized: enabled=False, requests_limit=60, interval_seconds=60\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.264681\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `b9ede7a7-596b-599e-940e-ccfce060237d`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.265265\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.266091\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.267318\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `b9ede7a7-596b-599e-940e-ccfce060237d`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.267691\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.268004\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.268633\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `b9ede7a7-596b-599e-940e-ccfce060237d`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.268942\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.269279\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.270173\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `b9ede7a7-596b-599e-940e-ccfce060237d`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.270600\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.270927\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.271469\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `b9ede7a7-596b-599e-940e-ccfce060237d`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.271775\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.272124\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.273307\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `b9ede7a7-596b-599e-940e-ccfce060237d`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.273562\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.273880\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.306722\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: pypdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.307177\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: text_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.307504\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: image_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.307810\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: audio_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.308094\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: unstructured_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.308357\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: advanced_pdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.327563\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.327978\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.328309\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `b9ede7a7-596b-599e-940e-ccfce060237d`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.329713\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.329970\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.330219\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `b9ede7a7-596b-599e-940e-ccfce060237d`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.333911\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.334210\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.334471\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `b9ede7a7-596b-599e-940e-ccfce060237d`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.340403\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.340936\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.341169\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `b9ede7a7-596b-599e-940e-ccfce060237d`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.369050\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.369650\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.369965\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `b9ede7a7-596b-599e-940e-ccfce060237d`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.393955\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.394440\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:33:26.394743\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `b9ede7a7-596b-599e-940e-ccfce060237d`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('7957d938-8b11-5dbb-8044-bd39e30da549'), dataset_id=UUID('4cc90c80-59e1-57db-8d4e-28f45f9d1661'), dataset_name='example', payload=None, data_ingestion_info=[{'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('7957d938-8b11-5dbb-8044-bd39e30da549'), dataset_id=UUID('4cc90c80-59e1-57db-8d4e-28f45f9d1661'), dataset_name='example', payload=None, data_ingestion_info=None), 'data_id': UUID('a9cc087f-1fe6-54d9-8626-06fb6bee185e')}, {'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('7957d938-8b11-5dbb-8044-bd39e30da549'), dataset_id=UUID('4cc90c80-59e1-57db-8d4e-28f45f9d1661'), dataset_name='example', payload=None, data_ingestion_info=None), 'data_id': UUID('2352a9c1-c822-59e1-a38a-a62fa0009143')}, {'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('7957d938-8b11-5dbb-8044-bd39e30da549'), dataset_id=UUID('4cc90c80-59e1-57db-8d4e-28f45f9d1661'), dataset_name='example', payload=None, data_ingestion_info=None), 'data_id': UUID('8175b7ba-1eeb-512e-9c9e-9ac7859cc505')}, {'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('7957d938-8b11-5dbb-8044-bd39e30da549'), dataset_id=UUID('4cc90c80-59e1-57db-8d4e-28f45f9d1661'), dataset_name='example', payload=None, data_ingestion_info=None), 'data_id': UUID('fb1b835a-d9ae-5599-ba17-3dcfb767f297')}, {'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('7957d938-8b11-5dbb-8044-bd39e30da549'), dataset_id=UUID('4cc90c80-59e1-57db-8d4e-28f45f9d1661'), dataset_name='example', payload=None, data_ingestion_info=None), 'data_id': UUID('9ce0cfb9-a3f7-5b95-b7e2-c8824363fa8a')}, {'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('7957d938-8b11-5dbb-8044-bd39e30da549'), dataset_id=UUID('4cc90c80-59e1-57db-8d4e-28f45f9d1661'), dataset_name='example', payload=None, data_ingestion_info=None), 'data_id': UUID('e64a82b1-6070-53a4-b631-cca67bce7d14')}])"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "import cognee\n",
     "\n",
@@ -561,881 +671,389 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "\u001b[2m2025-08-27T13:01:47.379592\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `e29ae05e-6381-5dff-a952-b7f7156a123f`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.364927\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `a68fd4c4-46a2-5aca-98d5-46646fa0cbec`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:01:47.554990\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.365793\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:01:47.737751\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.366370\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:01:47.869950\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.367252\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `a68fd4c4-46a2-5aca-98d5-46646fa0cbec`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:01:48.007947\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:01:48 - LiteLLM:INFO\u001b[0m: utils.py:2929 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:33:37.367570\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:03:13 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
+      "\u001b[2m2025-10-07T20:33:37.367948\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\u001b[92m14:03:13 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
+      "\u001b[2m2025-10-07T20:33:37.368650\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `a68fd4c4-46a2-5aca-98d5-46646fa0cbec`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.369534\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.282550\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.369944\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.320418\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.370804\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `a68fd4c4-46a2-5aca-98d5-46646fa0cbec`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.321107\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'dr. emily carter' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.371064\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.321469\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'education' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.371413\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.321779\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'ph.d. in computer science, stanford university' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.372107\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `a68fd4c4-46a2-5aca-98d5-46646fa0cbec`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.322113\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'b.s. in mathematics, university of california, berkeley' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.372428\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.322397\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'organization' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.372864\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.322732\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'innovateai labs' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.373605\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `a68fd4c4-46a2-5aca-98d5-46646fa0cbec`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.323048\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'datawave analytics' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.373898\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.323319\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'stanford university' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.374241\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.323719\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'university of california, berkeley' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.392711\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.324078\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'position' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.404807\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.324471\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'senior data scientist at innovateai labs' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.407830\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.324780\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'data scientist at datawave analytics' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.410319\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.325207\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'skill' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.412354\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.325515\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'python' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.414016\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.325718\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'r' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.420301\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.325964\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sql' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.427979\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.326255\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tensorflow' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.432593\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.326477\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'keras' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.439575\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.326728\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'scikit-learn' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.445716\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.327255\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'hadoop' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:37.456232\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.327861\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'spark' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:48.370377\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.328049\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tableau' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:48.420182\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLoaded JSON extension         \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.328312\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'matplotlib' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:48.455440\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.328590\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'natural language processing' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:48.456243\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'dr. emily carter' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.328763\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'deep learning' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:48.456685\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'organization' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.329041\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'predictive analytics' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:48.457029\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'stanford university' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.329242\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'machine learning' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:48.457363\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'university of california, berkeley' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.329454\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:48.457690\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'innovateai labs' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.329618\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2014' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:48.458019\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'datawave analytics' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.329834\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2010' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:48.458341\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'degree' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.329988\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2016' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:48.458618\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'ph.d. in computer science' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.330158\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'achievement' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:48.458876\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'b.s. in mathematics' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:13.330367\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'improved prediction accuracy by 25%' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:03:13 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:50.397043\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:03:14 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:51.351674\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:03:15 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:51.358793\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:03:15 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:51.360301\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'david thompson' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:03:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:51.361050\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'organization' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:51.361631\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'creativeworks agency' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:16.127289\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:03:16 - LiteLLM:INFO\u001b[0m: utils.py:2929 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:33:51.362581\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'visual innovations' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:03:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
+      "\u001b[2m2025-10-07T20:33:51.363138\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'educational_institution' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\u001b[92m14:03:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
+      "\u001b[2m2025-10-07T20:33:51.363844\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'rhode island school of design' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:51.364552\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'degree' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:24.159354\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:03:25 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:51.365273\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'b.f.a. in graphic design' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:03:25 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:51.365922\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:03:25 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:51.366327\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2012' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:03:26 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:51.366630\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2015' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:03:27 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:51.367065\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2015-present' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:03:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:53.924808\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:55.543740\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:28.025361\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.440785\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:28.170836\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.446845\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:28.306326\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.447421\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sarah nguyen' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:28.446538\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.447928\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'degree' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:28.579414\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.448478\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'm.s. in statistics' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:28.712543\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.449018\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'b.s. in applied mathematics' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:28.841720\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `e29ae05e-6381-5dff-a952-b7f7156a123f`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.449488\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'company' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:28.971284\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `e29ae05e-6381-5dff-a952-b7f7156a123f`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.450019\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'quantumtech' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:29.100235\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.450742\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'datacore solutions' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:29.233945\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.451246\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'programming language' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:29.390158\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.451757\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'python' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:03:29.533576\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:03:29 - LiteLLM:INFO\u001b[0m: utils.py:2929 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:33:56.452305\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'r' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:04:50 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
+      "\u001b[2m2025-10-07T20:33:56.452770\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'machine learning framework' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\u001b[92m14:04:50 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
+      "\u001b[2m2025-10-07T20:33:56.453216\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pytorch' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.453631\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'scikit-learn' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.132445\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.454047\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'statistical analysis software' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.140870\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.454425\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sas' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.141437\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'michael rodriguez' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.454815\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'spss' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.141811\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'degree' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.455234\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cloud platform' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.142102\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'm.s. in data science, carnegie mellon university (2013)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.455609\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'aws' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.142405\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'b.s. in computer science, university of michigan (2011)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.456014\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'azure' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.142706\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'organization' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.456536\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.143079\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'carnegie mellon university' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.456927\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'university of washington' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.143669\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'university of michigan' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.457388\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'university of texas at austin' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.144377\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'job' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.501611\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.146600\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'senior data scientist, alpha analytics (2017 – present)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.505241\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'company' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.148160\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'data scientist, techinsights (2013 – 2017)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.505755\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'technova solutions' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.148944\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'alpha analytics' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.506086\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'job_title' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.149419\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'techinsights' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.506420\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'senior data scientist' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.149899\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.506687\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'location' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.150373\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2017' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.506949\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'san francisco, ca' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.150637\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2013' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.507226\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'field' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.150911\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2011' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.507508\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'machine learning' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.151386\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'skill' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.507751\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'data science' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.152026\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'python' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.507994\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'programming_language' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.152702\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'java' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.508283\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'python' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.153306\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sql' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.508571\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'r' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.153722\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'scikit-learn' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.508845\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sql' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.153915\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'xgboost' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.509066\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'deep_learning_framework' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.154201\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'seaborn' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.509327\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tensorflow' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.154668\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'plotly' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.509605\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pytorch' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.155091\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mysql' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.509855\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'academic_qualification' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.155395\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mongodb' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.510156\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'masters or ph.d. in data science' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.155674\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'machine learning' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.510369\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'experience' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:50.155892\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'statistical modeling' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:04:50 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:56.510617\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '5+ years experience' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:04:50 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:56.909307\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:04:51 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:56.912471\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:04:52 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:56.912916\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'michael rodriguez' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:04:53 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:56.913239\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'organization' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.913593\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'alpha analytics' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:04:53.183427\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:04:53 - LiteLLM:INFO\u001b[0m: utils.py:2929 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:33:56.913979\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'techinsights' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:05:05 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
+      "\u001b[2m2025-10-07T20:33:56.914278\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'carnegie mellon university' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\u001b[92m14:05:05 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
+      "\u001b[2m2025-10-07T20:33:56.914655\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'university of michigan' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:56.914927\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:05.322305\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:05:05 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:56.915151\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2013' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:05:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:56.915371\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2011' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:05:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:56.915658\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'profession' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:05:07 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:56.916228\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'senior data scientist' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:05:07 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:56.916564\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'data scientist' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:05:08 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:33:57.029740\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.034344\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:08.880095\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.034871\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'jessica miller' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:09.011845\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.035333\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'organization' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:09.139270\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.035762\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'global enterprises' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:09.287708\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.036181\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'market leaders inc' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:09.485773\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.036543\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'educationalinstitution' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:09.625262\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.036875\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'university of southern california' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:09.763675\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `e29ae05e-6381-5dff-a952-b7f7156a123f`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.037182\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'fieldofstudy' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:09.933624\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `e29ae05e-6381-5dff-a952-b7f7156a123f`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.037535\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'business administration' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:10.078157\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.037882\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'profession' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:10.222889\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.038189\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sales manager' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:10.380248\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.038472\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sales representative' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:05:10.536508\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:05:10 - LiteLLM:INFO\u001b[0m: utils.py:2929 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:33:57.038860\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'skill' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:06:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
+      "\u001b[2m2025-10-07T20:33:57.039102\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sales strategy and planning' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\u001b[92m14:06:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
+      "\u001b[2m2025-10-07T20:33:57.039364\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'team leadership and development' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.039673\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'crm software' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.019994\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.040029\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'negotiation and relationship building' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.026138\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.040613\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.027020\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sarah nguyen' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.040897\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2010' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.027427\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'organization' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.041191\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2013' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.027629\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'quantumtech' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.041458\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2015' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.028008\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'datacore solutions' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.041729\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2015-present' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.028180\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'degree' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.519924\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.028485\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'm.s. in statistics' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.623680\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.028892\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'b.s. in applied mathematics' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.624187\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.029151\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'university of washington' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.624457\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.029443\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'university of texas at austin' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.624741\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.030216\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.624985\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.031108\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2014' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.625245\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.031843\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2012' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:57.625479\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `a68fd4c4-46a2-5aca-98d5-46646fa0cbec`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.032486\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2016' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:58.292226\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.033071\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'present' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:58.300823\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.033364\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'skill' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:58.827732\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.033876\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'python' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:59.040051\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.036096\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'r' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:59.648684\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.036641\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pytorch' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:59.649221\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.037043\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'scikit-learn' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:59.649550\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.038085\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sas' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:59.649845\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.038562\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'spss' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:59.650136\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.038903\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'aws' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:59.650723\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.039244\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'azure' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:33:59.650926\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `a68fd4c4-46a2-5aca-98d5-46646fa0cbec`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.039529\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'position' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:01.349738\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.039730\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'data scientist (quantumtech)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:03.022925\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.039942\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'junior data scientist (datacore solutions)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:03.680974\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.040135\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'achievement' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:03.976034\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:24.040332\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'improved model efficiency by 20%' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:06:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:34:03.976591\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:06:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:34:03.976959\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:06:25 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:34:03.977216\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:06:26 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:34:03.977514\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:06:26 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:34:03.977819\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:03.978068\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `a68fd4c4-46a2-5aca-98d5-46646fa0cbec`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:27.001049\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:06:27 - LiteLLM:INFO\u001b[0m: utils.py:2929 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:34:05.183360\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:06:34 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
+      "\u001b[2m2025-10-07T20:34:05.183819\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\u001b[92m14:06:34 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
+      "\u001b[2m2025-10-07T20:34:05.184132\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:05.184426\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:34.782530\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:06:35 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:34:05.184708\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:06:35 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:34:05.185092\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:06:36 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:34:05.185378\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `a68fd4c4-46a2-5aca-98d5-46646fa0cbec`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:06:36 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:34:05.323602\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:06:37 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:34:06.166424\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:06:37 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
+      "\u001b[2m2025-10-07T20:34:06.166969\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:06.167301\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:37.896055\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:06.168035\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:38.023334\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:06.168356\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:38.163692\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:06.168621\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:38.306820\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:06.168897\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `a68fd4c4-46a2-5aca-98d5-46646fa0cbec`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:38.437716\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:07.850334\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:38.566678\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:07.851074\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:38.701049\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `e29ae05e-6381-5dff-a952-b7f7156a123f`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:07.851488\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:38.837828\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `e29ae05e-6381-5dff-a952-b7f7156a123f`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:07.851921\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:38.971017\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:07.852348\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:39.106825\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:07.852612\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:06:39.269402\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:06:39.416821\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:06:39 - LiteLLM:INFO\u001b[0m: utils.py:2929 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:07:39 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\u001b[92m14:07:39 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.076839\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.089869\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.090647\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'david thompson' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.091047\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'contact' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.091481\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'david.thompson@example.com' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.091804\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '(555) 456-7890' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.092181\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'education' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.092559\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'rhode island school of design' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.092896\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'organization' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.093203\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'creativeworks agency' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.093480\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'visual innovations' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.093732\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'job' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.094071\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'senior graphic designer (creativeworks agency)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.094411\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'graphic designer (visual innovations)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.094677\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.095087\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2012' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.095387\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2015' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.095716\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'software' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.096076\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'adobe photoshop' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.096539\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'adobe illustrator' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.096817\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'adobe indesign' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.097038\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'skill' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.097309\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'html' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.097678\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'css' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.097934\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'specialty' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.098206\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'branding and identity' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:39.098423\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'typography' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:07:39 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:07:39 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:07:41 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:07:42 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:07:42 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:42.898490\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:07:43 - LiteLLM:INFO\u001b[0m: utils.py:2929 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:07:50 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\u001b[92m14:07:50 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:50.774170\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:07:51 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:07:51 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:07:51 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:07:52 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:07:55 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:07:56 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:56.710744\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:56.844417\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:56.974409\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:57.120036\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:57.258343\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:57.389231\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:57.519095\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `e29ae05e-6381-5dff-a952-b7f7156a123f`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:57.648012\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `e29ae05e-6381-5dff-a952-b7f7156a123f`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:57.777905\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:57.903188\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:58.041288\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:07:58.183908\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:07:58 - LiteLLM:INFO\u001b[0m: utils.py:2929 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:09:25 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\u001b[92m14:09:25 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.506882\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.514484\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.515173\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'jessica miller' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.515608\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'email' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.515918\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'jessica.miller@example.com' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.516371\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'phone' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.516680\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '(555) 567-8901' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.517023\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'degree' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.517342\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'b.a. in business administration' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.517660\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'organization' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.517900\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'university of southern california' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.518202\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.518556\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2010' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.518816\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'global enterprises' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.519156\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'market leaders inc.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.519462\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'job title' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.519738\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sales manager' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.520084\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sales representative' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.520341\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2015' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.520631\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'present' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.520908\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'achievement' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.521183\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'managed a sales team of 15' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.521489\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '20% increase in annual revenue' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.521725\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'expanded customer base by 25%' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.521963\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'award' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.522325\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'top salesperson award (2013)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.522600\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2013' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.522861\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'skill' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.523133\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sales strategy and planning' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.523495\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'team leadership and development' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.523776\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'negotiation and relationship building' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.524073\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'software' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.524355\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'salesforce' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:25.524716\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'zoho' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:09:26 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:09:26 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:09:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:09:29 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:09:31 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:31.465804\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:09:31 - LiteLLM:INFO\u001b[0m: utils.py:2929 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:09:40 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\u001b[92m14:09:40 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:40.613929\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:09:41 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:09:41 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:09:42 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:09:44 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:09:45 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:09:46 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:46.891337\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:48.115206\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:52.397824\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:55.325055\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:55.712006\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:55.866332\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:56.078882\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `e29ae05e-6381-5dff-a952-b7f7156a123f`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:56.461802\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `e29ae05e-6381-5dff-a952-b7f7156a123f`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:58.451988\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:58.834324\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:59.456885\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:09:59.835685\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:09:59 - LiteLLM:INFO\u001b[0m: utils.py:2929 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:10:44 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\u001b[92m14:10:45 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.004741\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.013274\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'organization' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.013770\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'technova solutions' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.014148\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'job' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.014545\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'senior data scientist (machine learning)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.014916\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'location' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.015535\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'san francisco, ca' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.015856\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'team' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.016237\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'analytics team' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.016573\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'skill' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.016923\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'machine learning' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.017917\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'data science' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.018571\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'python' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.018975\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'r' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.019720\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sql' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.020396\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tensorflow' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.021063\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pytorch' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.021651\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'deep learning' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.021983\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'degree' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.022306\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'master or phd' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.022611\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'experience' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.022823\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '5+ years experience' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.023130\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'problem-solving' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.023387\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'attention to detail' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.023641\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mentoring' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.023928\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cross-functional collaboration' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.024195\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.024456\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'large, complex datasets' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.024705\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'responsibility' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.025003\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'predictive models integration' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.025196\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'stay updated with ml advancements' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.025624\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'analyze datasets and extract insights' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:45.025942\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'develop and implement ml algorithms' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:10:46 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:10:47 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:10:48 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:10:48 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:10:51 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:10:51.648268\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:10:52 - LiteLLM:INFO\u001b[0m: utils.py:2929 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:11:04 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\u001b[92m14:11:05 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2025-08-07\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2025-08-07\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:11:05.002175\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:11:10 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:11:10 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:11:11 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:11:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:11:13 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\u001b[92m14:11:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:11:16.526730\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:11:16.672123\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:11:16.807143\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:11:16.938931\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:11:17.131661\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:11:17.287410\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:11:17.455194\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `e29ae05e-6381-5dff-a952-b7f7156a123f`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n"
+      "\u001b[2m2025-10-07T20:34:07.852868\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `a68fd4c4-46a2-5aca-98d5-46646fa0cbec`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n"
      ]
     }
    ],
@@ -1455,7 +1073,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 14,
    "id": "9dd29caf28c272d1",
    "metadata": {
     "ExecuteTime": {
@@ -1469,17 +1087,9 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "\u001b[2m2025-08-27T13:14:03.046467\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted old log file: /Users/daulet/Desktop/dev/cognee-claude/logs/2025-08-26_12-32-51.log\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
-      "/Users/daulet/Desktop/dev/cognee-claude/.venv/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "\u001b[2m2025-10-07T20:34:17.282583\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph visualization saved as /Users/daulet/Desktop/dev/cognee-claude/notebooks/.artifacts/graph_visualization.html\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:14:03.841002\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLogging initialized           \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m \u001b[36mcognee_version\u001b[0m=\u001b[35m0.2.4-local\u001b[0m \u001b[36mdatabase_path\u001b[0m=\u001b[35m/Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m \u001b[36mgraph_database_name\u001b[0m=\u001b[35m\u001b[0m \u001b[36mos_info\u001b[0m=\u001b[35m'Darwin 24.5.0 (Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:43 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8132)'\u001b[0m \u001b[36mpython_version\u001b[0m=\u001b[35m3.12.7\u001b[0m \u001b[36mrelational_config\u001b[0m=\u001b[35mcognee_db\u001b[0m \u001b[36mstructlog_version\u001b[0m=\u001b[35m25.4.0\u001b[0m \u001b[36mvector_config\u001b[0m=\u001b[35mlancedb\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:14:03.841488\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase storage: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:14:05.798338\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph visualization saved as /Users/daulet/Desktop/dev/cognee-claude/notebooks/.artifacts/graph_visualization.html\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:14:05.799781\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mThe HTML file has been stored at path: /Users/daulet/Desktop/dev/cognee-claude/notebooks/.artifacts/graph_visualization.html\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
+      "\u001b[2m2025-10-07T20:34:17.283063\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mThe HTML file has been stored at path: /Users/daulet/Desktop/dev/cognee-claude/notebooks/.artifacts/graph_visualization.html\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
      ]
     }
    ],
@@ -1514,7 +1124,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 15,
    "id": "e5e7dfc8",
    "metadata": {
     "ExecuteTime": {
@@ -1523,28 +1133,20 @@
     }
    },
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\u001b[1mEmbeddingRateLimiter initialized: enabled=False, requests_limit=60, interval_seconds=60\u001b[0m\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'payload': {'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'created_at': 1756299996071, 'updated_at': 1756299996071, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'sarah nguyen'}, 'score': 0.5709534883499146}\n",
-      "{'id': 'b6365021-70ae-53ea-83e7-885714b56092', 'payload': {'id': 'b6365021-70ae-53ea-83e7-885714b56092', 'created_at': 1756300182609, 'updated_at': 1756300182609, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'jessica.miller@example.com'}, 'score': 0.7205207943916321}\n",
-      "{'id': '282e7e92-e3d5-5a27-96fd-f145d6ebf7ec', 'payload': {'id': '282e7e92-e3d5-5a27-96fd-f145d6ebf7ec', 'created_at': 1756300071900, 'updated_at': 1756300071900, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'david.thompson@example.com'}, 'score': 0.775915801525116}\n",
-      "{'id': '5066c251-53a3-5f4c-a650-f291057b4659', 'payload': {'id': '5066c251-53a3-5f4c-a650-f291057b4659', 'created_at': 1756300182609, 'updated_at': 1756300182609, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'salesforce'}, 'score': 1.3353958129882812}\n",
-      "{'id': 'd510e7a8-85a6-557e-be89-3bef491c190f', 'payload': {'id': 'd510e7a8-85a6-557e-be89-3bef491c190f', 'created_at': 1756300271229, 'updated_at': 1756300271229, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'san francisco, ca'}, 'score': 1.3495608568191528}\n",
-      "{'id': 'ea51c0df-d8c8-549b-8978-3bc56d2cdacc', 'payload': {'id': 'ea51c0df-d8c8-549b-8978-3bc56d2cdacc', 'created_at': 1756299906589, 'updated_at': 1756299906589, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'b.s. in computer science, university of michigan (2011)'}, 'score': 1.3630532026290894}\n",
-      "{'id': '6b726763-e259-5e91-b505-85284f8ea5ea', 'payload': {'id': '6b726763-e259-5e91-b505-85284f8ea5ea', 'created_at': 1756299996071, 'updated_at': 1756299996071, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'sas'}, 'score': 1.378708004951477}\n",
-      "{'id': 'f2daec66-8503-57ae-8ceb-b590a0593eeb', 'payload': {'id': 'f2daec66-8503-57ae-8ceb-b590a0593eeb', 'created_at': 1756300071900, 'updated_at': 1756300071900, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': '(555) 456-7890'}, 'score': 1.3842216730117798}\n",
-      "{'id': '3b2935d9-1f76-5e7b-8367-907b26efc873', 'payload': {'id': '3b2935d9-1f76-5e7b-8367-907b26efc873', 'created_at': 1756299906589, 'updated_at': 1756299906589, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'm.s. in data science, carnegie mellon university (2013)'}, 'score': 1.396019697189331}\n",
-      "{'id': '36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932', 'payload': {'id': '36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932', 'created_at': 1756300182609, 'updated_at': 1756300182609, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'jessica miller'}, 'score': 1.4042032957077026}\n"
+      "{'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'payload': {'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'created_at': 1759869243986, 'updated_at': 1759869243986, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'sarah nguyen'}, 'score': 0.5709534883499146}\n",
+      "{'id': '198e2ab8-75e9-5931-97ab-da9a5a8e188c', 'payload': {'id': '198e2ab8-75e9-5931-97ab-da9a5a8e188c', 'created_at': 1759869242254, 'updated_at': 1759869242254, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'san francisco, ca'}, 'score': 1.3495469093322754}\n",
+      "{'id': '6b726763-e259-5e91-b505-85284f8ea5ea', 'payload': {'id': '6b726763-e259-5e91-b505-85284f8ea5ea', 'created_at': 1759869243986, 'updated_at': 1759869243986, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'sas'}, 'score': 1.378708004951477}\n",
+      "{'id': '435dbd37-ab20-503c-9e99-ab8b8a3484e5', 'payload': {'id': '435dbd37-ab20-503c-9e99-ab8b8a3484e5', 'created_at': 1759869246443, 'updated_at': 1759869246443, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'senior data scientist'}, 'score': 1.3935251235961914}\n",
+      "{'id': '36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932', 'payload': {'id': '36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932', 'created_at': 1759869244531, 'updated_at': 1759869244531, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'jessica miller'}, 'score': 1.4042136669158936}\n",
+      "{'id': '73ae630f-7b09-5dce-8c18-45d0a57b30f9', 'payload': {'id': '73ae630f-7b09-5dce-8c18-45d0a57b30f9', 'created_at': 1759869246443, 'updated_at': 1759869246443, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'michael rodriguez'}, 'score': 1.4521194696426392}\n",
+      "{'id': 'df9b4927-8f23-54ca-8ac9-015ac74e348c', 'payload': {'id': 'df9b4927-8f23-54ca-8ac9-015ac74e348c', 'created_at': 1759869244531, 'updated_at': 1759869244531, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'sales manager'}, 'score': 1.45354425907135}\n",
+      "{'id': '570781f9-ae7c-546b-aa21-88c5754443f4', 'payload': {'id': '570781f9-ae7c-546b-aa21-88c5754443f4', 'created_at': 1759869242254, 'updated_at': 1759869242254, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': '5+ years experience'}, 'score': 1.456857442855835}\n",
+      "{'id': '29e771c8-4c3f-52de-9511-6b705878e130', 'payload': {'id': '29e771c8-4c3f-52de-9511-6b705878e130', 'created_at': 1759869236359, 'updated_at': 1759869236359, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'dr. emily carter'}, 'score': 1.4710627794265747}\n",
+      "{'id': 'd82673ff-ff5e-5436-bc8b-2967d4301b4f', 'payload': {'id': 'd82673ff-ff5e-5436-bc8b-2967d4301b4f', 'created_at': 1759869243986, 'updated_at': 1759869243986, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'm.s. in statistics'}, 'score': 1.4715948104858398}\n"
      ]
     }
    ],
@@ -1599,7 +1201,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 16,
    "id": "21a3e9a6",
    "metadata": {
     "ExecuteTime": {
@@ -1613,15 +1215,15 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "\u001b[2m2025-08-27T13:15:00.678844\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting completion generation for query: 'sarah nguyen'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:36.551256\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting summary retrieval for query: 'sarah nguyen'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:15:00.683634\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting summary retrieval for query: 'sarah nguyen'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:37.197175\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mFound 6 summaries from vector search\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:15:01.048173\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mFound 6 summaries from vector search\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:37.197911\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReturning 6 summary payloads  \u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:15:01.048720\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReturning 6 summary payloads  \u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:37.198373\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting completion generation for query: 'sarah nguyen'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:15:01.049052\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReturning context with 6 item(s)\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n"
+      "\u001b[2m2025-10-07T20:34:37.198826\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReturning context with 6 item(s)\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n"
      ]
     },
     {
@@ -1631,17 +1233,17 @@
       "\n",
       "\\Extracted summaries are:\n",
       "\n",
-      "{'id': 'd63c0626-f304-5b51-81be-b7a42cdb7d88', 'created_at': 1756299804334, 'updated_at': 1756299804334, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Senior Data Scientist with 8+ years’ experience in machine learning and predictive analytics, specializing in NLP, deep learning, and production model deployment.'}\n",
+      "{'id': '4c47f1ef-54a5-54c9-bc4f-f23c45477451', 'created_at': 1759869237535, 'updated_at': 1759869237535, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Experienced Graphic Designer with over 8 years in visual design and branding, skilled in Adobe Creative Suite, focused on crafting engaging visuals.'}\n",
       "\n",
-      "{'id': '9c02f5ca-e629-5930-b178-1c6bee059689', 'created_at': 1756300070938, 'updated_at': 1756300070938, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Graphic designer with 8+ years’ experience specializing in branding and visual design; skilled in Adobe Creative Suite and basic web design.'}\n",
+      "{'id': 'f99dc79b-af29-5f70-9fcb-5bb62790994a', 'created_at': 1759869241394, 'updated_at': 1759869241394, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Senior Data Scientist specializing in Machine Learning at TechNova Solutions.'}\n",
       "\n",
-      "{'id': '54db4268-2156-5ae2-ba54-8c6c0d9bd3ed', 'created_at': 1756299905496, 'updated_at': 1756299905496, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Experienced Data Scientist specializing in machine learning and statistical modeling, skilled at working with large datasets and turning data into actionable business outcomes.'}\n",
+      "{'id': 'df7d916e-6056-5302-ad95-b5c46d5dac42', 'created_at': 1759869245597, 'updated_at': 1759869245597, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Data Scientist proficient in machine learning and statistical analysis, experienced in managing extensive datasets and converting data into strategic business insights.'}\n",
       "\n",
-      "{'id': '799d1f2a-4c78-517f-b09b-ede659507d4d', 'created_at': 1756300180835, 'updated_at': 1756300180835, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Seasoned sales leader with a strong record of driving revenue growth and building high-performing teams.'}\n",
+      "{'id': '7144d310-9f4e-5b13-acaa-1f53bdd77cc0', 'created_at': 1759869243709, 'updated_at': 1759869243709, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Sales Manager with a proven history of driving revenue growth and cultivating effective teams. Strong leadership and communication abilities.'}\n",
       "\n",
-      "{'id': 'a3534071-8c78-5f37-99ea-0f14ea971422', 'created_at': 1756300269688, 'updated_at': 1756300269688, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'TechNova Solutions is hiring a Senior Data Scientist (Machine Learning) in San Francisco to design, train, and operationalize ML models, analyze large datasets, and guide junior team members.'}\n",
+      "{'id': '352ab868-e930-5009-a855-14b83894520d', 'created_at': 1759869243053, 'updated_at': 1759869243053, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Data Scientist with 6 years of experience in machine learning, focused on utilizing data for business improvements and product optimization.'}\n",
       "\n",
-      "{'id': '594514cb-0399-5389-a1d9-4d6873606c70', 'created_at': 1756299994959, 'updated_at': 1756299994959, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Data Scientist with 6 years’ experience in machine learning and statistical modeling, focused on financial forecasting and predictive analytics. Proven track record of boosting model efficiency by 20%; skilled in Python, R, PyTorch, scikit-learn, SAS, SPSS, and cloud platforms (AWS, Azure). Holds an M.S. in Statistics and a B.S. in Applied Mathematics.'}\n",
+      "{'id': '9b808a69-a954-5e68-af72-045c3e7f652a', 'created_at': 1759869235560, 'updated_at': 1759869235560, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Experienced Senior Data Scientist with 8+ years in machine learning and predictive analytics, proficient in creating advanced algorithms and deploying scalable models in production.'}\n",
       "\n"
      ]
     }
@@ -1668,7 +1270,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 17,
    "id": "c7a8abff",
    "metadata": {
     "ExecuteTime": {
@@ -1682,15 +1284,15 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "\u001b[2m2025-08-27T13:15:07.822953\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting completion generation for query: 'sarah nguyen'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mChunksRetriever\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:44.865101\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting chunk retrieval for query: 'sarah nguyen'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mChunksRetriever\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:15:07.823567\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting chunk retrieval for query: 'sarah nguyen'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mChunksRetriever\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:45.083571\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mFound 6 chunks from vector search\u001b[0m [\u001b[0m\u001b[1m\u001b[34mChunksRetriever\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:15:08.131266\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mFound 6 chunks from vector search\u001b[0m [\u001b[0m\u001b[1m\u001b[34mChunksRetriever\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:45.084214\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReturning 6 chunk payloads    \u001b[0m [\u001b[0m\u001b[1m\u001b[34mChunksRetriever\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:15:08.132088\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReturning 6 chunk payloads    \u001b[0m [\u001b[0m\u001b[1m\u001b[34mChunksRetriever\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:34:45.084687\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting completion generation for query: 'sarah nguyen'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mChunksRetriever\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:15:08.132522\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReturning context with 6 item(s)\u001b[0m [\u001b[0m\u001b[1m\u001b[34mChunksRetriever\u001b[0m]\u001b[0m\n"
+      "\u001b[2m2025-10-07T20:34:45.085107\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReturning context with 6 item(s)\u001b[0m [\u001b[0m\u001b[1m\u001b[34mChunksRetriever\u001b[0m]\u001b[0m\n"
      ]
     },
     {
@@ -1701,17 +1303,17 @@
       "\n",
       "Extracted chunks are:\n",
       "\n",
-      "{'id': 'e2a2fff5-44bc-5e49-bbca-901634f33033', 'created_at': 1756299995290, 'updated_at': 1756299995290, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': '\\nCV 3: Relevant\\nName: Sarah Nguyen\\nContact Information:\\n\\nEmail: sarah.nguyen@example.com\\nPhone: (555) 345-6789\\nSummary:\\n\\nData Scientist specializing in machine learning with 6 years of experience. Passionate about leveraging data to drive business solutions and improve product performance.\\n\\nEducation:\\n\\nM.S. in Statistics, University of Washington (2014)\\nB.S. in Applied Mathematics, University of Texas at Austin (2012)\\nExperience:\\n\\nData Scientist, QuantumTech (2016 – Present)\\nDesigned and implemented machine learning algorithms for financial forecasting.\\nImproved model efficiency by 20% through algorithm optimization.\\nJunior Data Scientist, DataCore Solutions (2014 – 2016)\\nAssisted in developing predictive models for supply chain optimization.\\nConducted data cleaning and preprocessing on large datasets.\\nSkills:\\n\\nProgramming Languages: Python, R\\nMachine Learning Frameworks: PyTorch, Scikit-Learn\\nStatistical Analysis: SAS, SPSS\\nCloud Platforms: AWS, Azure\\n'}\n",
+      "{'id': 'b8730838-071e-542f-9bba-83de86d7a56b', 'created_at': 1759869243385, 'updated_at': 1759869243385, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': '\\nCV 3: Relevant\\nName: Sarah Nguyen\\nContact Information:\\n\\nEmail: sarah.nguyen@example.com\\nPhone: (555) 345-6789\\nSummary:\\n\\nData Scientist specializing in machine learning with 6 years of experience. Passionate about leveraging data to drive business solutions and improve product performance.\\n\\nEducation:\\n\\nM.S. in Statistics, University of Washington (2014)\\nB.S. in Applied Mathematics, University of Texas at Austin (2012)\\nExperience:\\n\\nData Scientist, QuantumTech (2016 – Present)\\nDesigned and implemented machine learning algorithms for financial forecasting.\\nImproved model efficiency by 20% through algorithm optimization.\\nJunior Data Scientist, DataCore Solutions (2014 – 2016)\\nAssisted in developing predictive models for supply chain optimization.\\nConducted data cleaning and preprocessing on large datasets.\\nSkills:\\n\\nProgramming Languages: Python, R\\nMachine Learning Frameworks: PyTorch, Scikit-Learn\\nStatistical Analysis: SAS, SPSS\\nCloud Platforms: AWS, Azure\\n'}\n",
       "\n",
-      "{'id': '075c882b-ae90-50c0-bc60-71c8da1d898d', 'created_at': 1756300181483, 'updated_at': 1756300181483, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': \"\\nCV 5: Not Relevant\\nName: Jessica Miller\\nContact Information:\\n\\nEmail: jessica.miller@example.com\\nPhone: (555) 567-8901\\nSummary:\\n\\nExperienced Sales Manager with a strong track record in driving sales growth and building high-performing teams. Excellent communication and leadership skills.\\n\\nEducation:\\n\\nB.A. in Business Administration, University of Southern California (2010)\\nExperience:\\n\\nSales Manager, Global Enterprises (2015 – Present)\\nManaged a sales team of 15 members, achieving a 20% increase in annual revenue.\\nDeveloped sales strategies that expanded customer base by 25%.\\nSales Representative, Market Leaders Inc. (2010 – 2015)\\nConsistently exceeded sales targets and received the 'Top Salesperson' award in 2013.\\nSkills:\\n\\nSales Strategy and Planning\\nTeam Leadership and Development\\nCRM Software: Salesforce, Zoho\\nNegotiation and Relationship Building\\n\"}\n",
+      "{'id': '51c1e778-f0fe-5cfa-bb0b-8c7a8a28aae5', 'created_at': 1759869243982, 'updated_at': 1759869243982, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': \"\\nCV 5: Not Relevant\\nName: Jessica Miller\\nContact Information:\\n\\nEmail: jessica.miller@example.com\\nPhone: (555) 567-8901\\nSummary:\\n\\nExperienced Sales Manager with a strong track record in driving sales growth and building high-performing teams. Excellent communication and leadership skills.\\n\\nEducation:\\n\\nB.A. in Business Administration, University of Southern California (2010)\\nExperience:\\n\\nSales Manager, Global Enterprises (2015 – Present)\\nManaged a sales team of 15 members, achieving a 20% increase in annual revenue.\\nDeveloped sales strategies that expanded customer base by 25%.\\nSales Representative, Market Leaders Inc. (2010 – 2015)\\nConsistently exceeded sales targets and received the 'Top Salesperson' award in 2013.\\nSkills:\\n\\nSales Strategy and Planning\\nTeam Leadership and Development\\nCRM Software: Salesforce, Zoho\\nNegotiation and Relationship Building\\n\"}\n",
       "\n",
-      "{'id': '0af63ca5-47a0-50f3-b4d8-3463a1d0a749', 'created_at': 1756300071327, 'updated_at': 1756300071327, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': '\\nCV 4: Not Relevant\\nName: David Thompson\\nContact Information:\\n\\nEmail: david.thompson@example.com\\nPhone: (555) 456-7890\\nSummary:\\n\\nCreative Graphic Designer with over 8 years of experience in visual design and branding. Proficient in Adobe Creative Suite and passionate about creating compelling visuals.\\n\\nEducation:\\n\\nB.F.A. in Graphic Design, Rhode Island School of Design (2012)\\nExperience:\\n\\nSenior Graphic Designer, CreativeWorks Agency (2015 – Present)\\nLed design projects for clients in various industries.\\nCreated branding materials that increased client engagement by 30%.\\nGraphic Designer, Visual Innovations (2012 – 2015)\\nDesigned marketing collateral, including brochures, logos, and websites.\\nCollaborated with the marketing team to develop cohesive brand strategies.\\nSkills:\\n\\nDesign Software: Adobe Photoshop, Illustrator, InDesign\\nWeb Design: HTML, CSS\\nSpecialties: Branding and Identity, Typography\\n'}\n",
+      "{'id': 'e7c43949-a4d6-5cdc-90e0-a7046a528a95', 'created_at': 1759869237781, 'updated_at': 1759869237781, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': '\\nCV 4: Not Relevant\\nName: David Thompson\\nContact Information:\\n\\nEmail: david.thompson@example.com\\nPhone: (555) 456-7890\\nSummary:\\n\\nCreative Graphic Designer with over 8 years of experience in visual design and branding. Proficient in Adobe Creative Suite and passionate about creating compelling visuals.\\n\\nEducation:\\n\\nB.F.A. in Graphic Design, Rhode Island School of Design (2012)\\nExperience:\\n\\nSenior Graphic Designer, CreativeWorks Agency (2015 – Present)\\nLed design projects for clients in various industries.\\nCreated branding materials that increased client engagement by 30%.\\nGraphic Designer, Visual Innovations (2012 – 2015)\\nDesigned marketing collateral, including brochures, logos, and websites.\\nCollaborated with the marketing team to develop cohesive brand strategies.\\nSkills:\\n\\nDesign Software: Adobe Photoshop, Illustrator, InDesign\\nWeb Design: HTML, CSS\\nSpecialties: Branding and Identity, Typography\\n'}\n",
       "\n",
-      "{'id': '15190e7c-0ec2-5d99-ae68-5d76cb6bb414', 'created_at': 1756299805159, 'updated_at': 1756299805159, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': '\\nCV 1: Relevant\\nName: Dr. Emily Carter\\nContact Information:\\n\\nEmail: emily.carter@example.com\\nPhone: (555) 123-4567\\nSummary:\\n\\nSenior Data Scientist with over 8 years of experience in machine learning and predictive analytics. Expertise in developing advanced algorithms and deploying scalable models in production environments.\\n\\nEducation:\\n\\nPh.D. in Computer Science, Stanford University (2014)\\nB.S. in Mathematics, University of California, Berkeley (2010)\\nExperience:\\n\\nSenior Data Scientist, InnovateAI Labs (2016 – Present)\\nLed a team in developing machine learning models for natural language processing applications.\\nImplemented deep learning algorithms that improved prediction accuracy by 25%.\\nCollaborated with cross-functional teams to integrate models into cloud-based platforms.\\nData Scientist, DataWave Analytics (2014 – 2016)\\nDeveloped predictive models for customer segmentation and churn analysis.\\nAnalyzed large datasets using Hadoop and Spark frameworks.\\nSkills:\\n\\nProgramming Languages: Python, R, SQL\\nMachine Learning: TensorFlow, Keras, Scikit-Learn\\nBig Data Technologies: Hadoop, Spark\\nData Visualization: Tableau, Matplotlib\\n'}\n",
+      "{'id': 'beb4b9bc-703c-5e20-8512-d4468c849277', 'created_at': 1759869235792, 'updated_at': 1759869235792, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': '\\nCV 1: Relevant\\nName: Dr. Emily Carter\\nContact Information:\\n\\nEmail: emily.carter@example.com\\nPhone: (555) 123-4567\\nSummary:\\n\\nSenior Data Scientist with over 8 years of experience in machine learning and predictive analytics. Expertise in developing advanced algorithms and deploying scalable models in production environments.\\n\\nEducation:\\n\\nPh.D. in Computer Science, Stanford University (2014)\\nB.S. in Mathematics, University of California, Berkeley (2010)\\nExperience:\\n\\nSenior Data Scientist, InnovateAI Labs (2016 – Present)\\nLed a team in developing machine learning models for natural language processing applications.\\nImplemented deep learning algorithms that improved prediction accuracy by 25%.\\nCollaborated with cross-functional teams to integrate models into cloud-based platforms.\\nData Scientist, DataWave Analytics (2014 – 2016)\\nDeveloped predictive models for customer segmentation and churn analysis.\\nAnalyzed large datasets using Hadoop and Spark frameworks.\\nSkills:\\n\\nProgramming Languages: Python, R, SQL\\nMachine Learning: TensorFlow, Keras, Scikit-Learn\\nBig Data Technologies: Hadoop, Spark\\nData Visualization: Tableau, Matplotlib\\n'}\n",
       "\n",
-      "{'id': 'fde5c9b9-ff07-5f7a-ba70-afc421666787', 'created_at': 1756299905819, 'updated_at': 1756299905819, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': '\\nCV 2: Relevant\\nName: Michael Rodriguez\\nContact Information:\\n\\nEmail: michael.rodriguez@example.com\\nPhone: (555) 234-5678\\nSummary:\\n\\nData Scientist with a strong background in machine learning and statistical modeling. Skilled in handling large datasets and translating data into actionable business insights.\\n\\nEducation:\\n\\nM.S. in Data Science, Carnegie Mellon University (2013)\\nB.S. in Computer Science, University of Michigan (2011)\\nExperience:\\n\\nSenior Data Scientist, Alpha Analytics (2017 – Present)\\nDeveloped machine learning models to optimize marketing strategies.\\nReduced customer acquisition cost by 15% through predictive modeling.\\nData Scientist, TechInsights (2013 – 2017)\\nAnalyzed user behavior data to improve product features.\\nImplemented A/B testing frameworks to evaluate product changes.\\nSkills:\\n\\nProgramming Languages: Python, Java, SQL\\nMachine Learning: Scikit-Learn, XGBoost\\nData Visualization: Seaborn, Plotly\\nDatabases: MySQL, MongoDB\\n'}\n",
+      "{'id': '2d052615-b28f-511c-ac15-1bdb7a155ad7', 'created_at': 1759869245851, 'updated_at': 1759869245851, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': '\\nCV 2: Relevant\\nName: Michael Rodriguez\\nContact Information:\\n\\nEmail: michael.rodriguez@example.com\\nPhone: (555) 234-5678\\nSummary:\\n\\nData Scientist with a strong background in machine learning and statistical modeling. Skilled in handling large datasets and translating data into actionable business insights.\\n\\nEducation:\\n\\nM.S. in Data Science, Carnegie Mellon University (2013)\\nB.S. in Computer Science, University of Michigan (2011)\\nExperience:\\n\\nSenior Data Scientist, Alpha Analytics (2017 – Present)\\nDeveloped machine learning models to optimize marketing strategies.\\nReduced customer acquisition cost by 15% through predictive modeling.\\nData Scientist, TechInsights (2013 – 2017)\\nAnalyzed user behavior data to improve product features.\\nImplemented A/B testing frameworks to evaluate product changes.\\nSkills:\\n\\nProgramming Languages: Python, Java, SQL\\nMachine Learning: Scikit-Learn, XGBoost\\nData Visualization: Seaborn, Plotly\\nDatabases: MySQL, MongoDB\\n'}\n",
       "\n",
-      "{'id': '15790448-7267-5a84-9dd7-be4997889842', 'created_at': 1756300270349, 'updated_at': 1756300270349, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Senior Data Scientist (Machine Learning)\\n\\nCompany: TechNova Solutions\\nLocation: San Francisco, CA\\n\\nJob Description:\\n\\nTechNova Solutions is seeking a Senior Data Scientist specializing in Machine Learning to join our dynamic analytics team. The ideal candidate will have a strong background in developing and deploying machine learning models, working with large datasets, and translating complex data into actionable insights.\\n\\nResponsibilities:\\n\\nDevelop and implement advanced machine learning algorithms and models.\\nAnalyze large, complex datasets to extract meaningful patterns and insights.\\nCollaborate with cross-functional teams to integrate predictive models into products.\\nStay updated with the latest advancements in machine learning and data science.\\nMentor junior data scientists and provide technical guidance.\\nQualifications:\\n\\nMaster’s or Ph.D. in Data Science, Computer Science, Statistics, or a related field.\\n5+ years of experience in data science and machine learning.\\nProficient in Python, R, and SQL.\\nExperience with deep learning frameworks (e.g., TensorFlow, PyTorch).\\nStrong problem-solving skills and attention to detail.\\nCandidate CVs\\n'}\n",
+      "{'id': '1d3c1a95-e2ec-562a-a326-2eadfa556bf4', 'created_at': 1759869241747, 'updated_at': 1759869241747, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'Senior Data Scientist (Machine Learning)\\n\\nCompany: TechNova Solutions\\nLocation: San Francisco, CA\\n\\nJob Description:\\n\\nTechNova Solutions is seeking a Senior Data Scientist specializing in Machine Learning to join our dynamic analytics team. The ideal candidate will have a strong background in developing and deploying machine learning models, working with large datasets, and translating complex data into actionable insights.\\n\\nResponsibilities:\\n\\nDevelop and implement advanced machine learning algorithms and models.\\nAnalyze large, complex datasets to extract meaningful patterns and insights.\\nCollaborate with cross-functional teams to integrate predictive models into products.\\nStay updated with the latest advancements in machine learning and data science.\\nMentor junior data scientists and provide technical guidance.\\nQualifications:\\n\\nMaster’s or Ph.D. in Data Science, Computer Science, Statistics, or a related field.\\n5+ years of experience in data science and machine learning.\\nProficient in Python, R, and SQL.\\nExperience with deep learning frameworks (e.g., TensorFlow, PyTorch).\\nStrong problem-solving skills and attention to detail.\\nCandidate CVs\\n'}\n",
       "\n"
      ]
     }
@@ -1733,7 +1335,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 18,
    "id": "706a3954",
    "metadata": {},
    "outputs": [
@@ -1745,51 +1347,43 @@
       "\n",
       "Extracted sentences are:\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'is_a', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'updated_at': '2025-08-27 13:06:34'}, {'id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'name': 'person', 'type': 'EntityType', 'created_at': 1756300165515, 'updated_at': 1756300165515, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'person'})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'is_a', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'updated_at': '2025-10-07 20:34:03'}, {'id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'name': 'person', 'type': 'EntityType', 'created_at': 1759869236912, 'updated_at': 1759869236912, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'person'})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'has_skill', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': 'c95db510-e2ee-5a00-bded-20bbcb50c492', 'ontology_valid': False}, {'id': 'c95db510-e2ee-5a00-bded-20bbcb50c492', 'name': 'python', 'type': 'Entity', 'created_at': 1756300245018, 'updated_at': 1756300245018, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Programming language used for data science and machine learning.'})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'uses', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': 'c95db510-e2ee-5a00-bded-20bbcb50c492', 'ontology_valid': False}, {'id': 'c95db510-e2ee-5a00-bded-20bbcb50c492', 'name': 'python', 'type': 'Entity', 'created_at': 1759869236452, 'updated_at': 1759869236452, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Programming language used by Sarah Nguyen.'})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'has_skill', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '39bd9707-8098-52ed-9cbf-bbdd26b963fb', 'ontology_valid': False}, {'id': '39bd9707-8098-52ed-9cbf-bbdd26b963fb', 'name': 'r', 'type': 'Entity', 'created_at': 1756300245019, 'updated_at': 1756300245019, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Programming language for statistical analysis.'})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'uses', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '39bd9707-8098-52ed-9cbf-bbdd26b963fb', 'ontology_valid': False}, {'id': '39bd9707-8098-52ed-9cbf-bbdd26b963fb', 'name': 'r', 'type': 'Entity', 'created_at': 1759869236452, 'updated_at': 1759869236452, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Programming language used by Sarah Nguyen.'})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'contains', 'source_node_id': 'e2a2fff5-44bc-5e49-bbca-901634f33033', 'target_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'updated_at': '2025-08-27 13:06:34'}, {'id': 'e2a2fff5-44bc-5e49-bbca-901634f33033', 'name': '', 'type': 'DocumentChunk', 'created_at': 1756299910531, 'updated_at': 1756299910531, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'belongs_to_set': None, 'text': '\\nCV 3: Relevant\\nName: Sarah Nguyen\\nContact Information:\\n\\nEmail: sarah.nguyen@example.com\\nPhone: (555) 345-6789\\nSummary:\\n\\nData Scientist specializing in machine learning with 6 years of experience. Passionate about leveraging data to drive business solutions and improve product performance.\\n\\nEducation:\\n\\nM.S. in Statistics, University of Washington (2014)\\nB.S. in Applied Mathematics, University of Texas at Austin (2012)\\nExperience:\\n\\nData Scientist, QuantumTech (2016 – Present)\\nDesigned and implemented machine learning algorithms for financial forecasting.\\nImproved model efficiency by 20% through algorithm optimization.\\nJunior Data Scientist, DataCore Solutions (2014 – 2016)\\nAssisted in developing predictive models for supply chain optimization.\\nConducted data cleaning and preprocessing on large datasets.\\nSkills:\\n\\nProgramming Languages: Python, R\\nMachine Learning Frameworks: PyTorch, Scikit-Learn\\nStatistical Analysis: SAS, SPSS\\nCloud Platforms: AWS, Azure\\n', 'chunk_size': 329, 'chunk_index': 0, 'cut_type': 'sentence_cut'})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'uses', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': 'c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6', 'ontology_valid': False}, {'id': 'c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6', 'name': 'pytorch', 'type': 'Entity', 'created_at': 1759869236453, 'updated_at': 1759869236453, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Machine learning framework used by Sarah Nguyen.'})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'has_degree', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': 'aab60399-8979-5c71-bf42-0c3d41593871', 'ontology_valid': False}, {'id': 'aab60399-8979-5c71-bf42-0c3d41593871', 'name': 'm.s. in statistics', 'type': 'Entity', 'created_at': 1756299984028, 'updated_at': 1756299984028, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'institution: University of Washington\\ncompletion_date: Date_2014'})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'contains', 'source_node_id': 'b8730838-071e-542f-9bba-83de86d7a56b', 'target_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'updated_at': '2025-10-07 20:34:03'}, {'id': 'b8730838-071e-542f-9bba-83de86d7a56b', 'name': '', 'type': 'DocumentChunk', 'created_at': 1759869217411, 'updated_at': 1759869217411, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'belongs_to_set': None, 'text': '\\nCV 3: Relevant\\nName: Sarah Nguyen\\nContact Information:\\n\\nEmail: sarah.nguyen@example.com\\nPhone: (555) 345-6789\\nSummary:\\n\\nData Scientist specializing in machine learning with 6 years of experience. Passionate about leveraging data to drive business solutions and improve product performance.\\n\\nEducation:\\n\\nM.S. in Statistics, University of Washington (2014)\\nB.S. in Applied Mathematics, University of Texas at Austin (2012)\\nExperience:\\n\\nData Scientist, QuantumTech (2016 – Present)\\nDesigned and implemented machine learning algorithms for financial forecasting.\\nImproved model efficiency by 20% through algorithm optimization.\\nJunior Data Scientist, DataCore Solutions (2014 – 2016)\\nAssisted in developing predictive models for supply chain optimization.\\nConducted data cleaning and preprocessing on large datasets.\\nSkills:\\n\\nProgramming Languages: Python, R\\nMachine Learning Frameworks: PyTorch, Scikit-Learn\\nStatistical Analysis: SAS, SPSS\\nCloud Platforms: AWS, Azure\\n', 'chunk_size': 329, 'chunk_index': 0, 'cut_type': 'sentence_cut'})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'has_degree', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '4b4d74c0-999c-55dc-a8dd-eea5be5a90f1', 'ontology_valid': False}, {'id': '4b4d74c0-999c-55dc-a8dd-eea5be5a90f1', 'name': 'b.s. in applied mathematics', 'type': 'Entity', 'created_at': 1756299984029, 'updated_at': 1756299984029, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'institution: University of Texas at Austin\\ncompletion_date: Date_2012'})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'obtained', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': 'd82673ff-ff5e-5436-bc8b-2967d4301b4f', 'ontology_valid': False}, {'id': 'd82673ff-ff5e-5436-bc8b-2967d4301b4f', 'name': 'm.s. in statistics', 'type': 'Entity', 'created_at': 1759869236448, 'updated_at': 1759869236448, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': \"Master's degree in Statistics from University of Washington.\"})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'has_skill', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': 'c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6', 'ontology_valid': False}, {'id': 'c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6', 'name': 'pytorch', 'type': 'Entity', 'created_at': 1756300245021, 'updated_at': 1756300245021, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Deep learning framework.'})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'obtained', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '5abf79a8-2cdc-56a9-b78a-fd8150e9e891', 'ontology_valid': False}, {'id': '5abf79a8-2cdc-56a9-b78a-fd8150e9e891', 'name': 'b.s. in applied mathematics', 'type': 'Entity', 'created_at': 1759869236449, 'updated_at': 1759869236449, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': \"Bachelor's degree in Applied Mathematics from University of Texas at Austin.\"})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'has_skill', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': 'c689d93a-230a-566a-a4e6-8e461e56586c', 'ontology_valid': False}, {'id': 'c689d93a-230a-566a-a4e6-8e461e56586c', 'name': 'scikit-learn', 'type': 'Entity', 'created_at': 1756299984038, 'updated_at': 1756299984038, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': ''})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'works_at', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '0d980f2a-09dd-581e-acc3-cc2d87c1bab4', 'ontology_valid': False}, {'id': '0d980f2a-09dd-581e-acc3-cc2d87c1bab4', 'name': 'quantumtech', 'type': 'Entity', 'created_at': 1759869236450, 'updated_at': 1759869236450, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Company where Sarah Nguyen works as a Data Scientist.'})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'has_skill', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '6b726763-e259-5e91-b505-85284f8ea5ea', 'ontology_valid': False}, {'id': '6b726763-e259-5e91-b505-85284f8ea5ea', 'name': 'sas', 'type': 'Entity', 'created_at': 1756299984038, 'updated_at': 1756299984038, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': ''})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'worked_at', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '95ac0551-38fc-5187-a422-533aeb7e8db0', 'ontology_valid': False}, {'id': '95ac0551-38fc-5187-a422-533aeb7e8db0', 'name': 'datacore solutions', 'type': 'Entity', 'created_at': 1759869236451, 'updated_at': 1759869236451, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Company where Sarah Nguyen worked as a Junior Data Scientist.'})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'has_skill', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '4bee5f9c-846b-50f7-96fd-3e5889872b10', 'ontology_valid': False}, {'id': '4bee5f9c-846b-50f7-96fd-3e5889872b10', 'name': 'spss', 'type': 'Entity', 'created_at': 1756299984038, 'updated_at': 1756299984038, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': ''})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'uses', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '37eecdcc-fb56-519c-bc18-d0d3afea0c0d', 'ontology_valid': False}, {'id': '37eecdcc-fb56-519c-bc18-d0d3afea0c0d', 'name': 'scikit-learn', 'type': 'Entity', 'created_at': 1759869236454, 'updated_at': 1759869236454, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Machine learning framework used by Sarah Nguyen.'})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'has_skill', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '3edcdf3f-25af-57a3-8878-8008bd7ea05a', 'ontology_valid': False}, {'id': '3edcdf3f-25af-57a3-8878-8008bd7ea05a', 'name': 'aws', 'type': 'Entity', 'created_at': 1756299984039, 'updated_at': 1756299984039, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': ''})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'uses', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '6b726763-e259-5e91-b505-85284f8ea5ea', 'ontology_valid': False}, {'id': '6b726763-e259-5e91-b505-85284f8ea5ea', 'name': 'sas', 'type': 'Entity', 'created_at': 1759869236454, 'updated_at': 1759869236454, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Statistical analysis software used by Sarah Nguyen.'})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'has_skill', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '8b431923-4aa2-5886-a661-b8de0f888a9b', 'ontology_valid': False}, {'id': '8b431923-4aa2-5886-a661-b8de0f888a9b', 'name': 'azure', 'type': 'Entity', 'created_at': 1756299984039, 'updated_at': 1756299984039, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': ''})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'uses', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '4bee5f9c-846b-50f7-96fd-3e5889872b10', 'ontology_valid': False}, {'id': '4bee5f9c-846b-50f7-96fd-3e5889872b10', 'name': 'spss', 'type': 'Entity', 'created_at': 1759869236455, 'updated_at': 1759869236455, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Statistical analysis software used by Sarah Nguyen.'})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'held_position', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '7ba500ab-9375-5eeb-9ada-ec931f3120a1', 'ontology_valid': False}, {'id': '7ba500ab-9375-5eeb-9ada-ec931f3120a1', 'name': 'data scientist (quantumtech)', 'type': 'Entity', 'created_at': 1756299984039, 'updated_at': 1756299984039, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'start_date: Date_2016\\nend_date: Date_Present\\nresponsibilities: Designed and implemented machine learning algorithms for financial forecasting; Improved model efficiency by 20% through algorithm optimization'})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'uses', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '3edcdf3f-25af-57a3-8878-8008bd7ea05a', 'ontology_valid': False}, {'id': '3edcdf3f-25af-57a3-8878-8008bd7ea05a', 'name': 'aws', 'type': 'Entity', 'created_at': 1759869236455, 'updated_at': 1759869236455, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Cloud platform used by Sarah Nguyen.'})\n",
       "\n",
-      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'}, {'relationship_name': 'held_position', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '7f9f181a-350c-5970-85d4-ca3f1703a089', 'ontology_valid': False}, {'id': '7f9f181a-350c-5970-85d4-ca3f1703a089', 'name': 'junior data scientist (datacore solutions)', 'type': 'Entity', 'created_at': 1756299984040, 'updated_at': 1756299984040, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'start_date: Date_2014\\nend_date: Date_2016\\nresponsibilities: Assisted in developing predictive models for supply chain optimization; Conducted data cleaning and preprocessing on large datasets'})\n",
+      "({'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'}, {'relationship_name': 'uses', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': '8b431923-4aa2-5886-a661-b8de0f888a9b', 'ontology_valid': False}, {'id': '8b431923-4aa2-5886-a661-b8de0f888a9b', 'name': 'azure', 'type': 'Entity', 'created_at': 1759869236456, 'updated_at': 1759869236456, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Cloud platform used by Sarah Nguyen.'})\n",
       "\n",
-      "({'id': 'dfa1b90a-397e-59c3-acf8-071fa2509968', 'name': 'email', 'type': 'EntityType', 'created_at': 1756300165515, 'updated_at': 1756300165515, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email'}, {'relationship_name': 'is_a', 'source_node_id': 'b6365021-70ae-53ea-83e7-885714b56092', 'target_node_id': 'dfa1b90a-397e-59c3-acf8-071fa2509968', 'updated_at': '2025-08-27 13:09:40'}, {'id': 'b6365021-70ae-53ea-83e7-885714b56092', 'name': 'jessica.miller@example.com', 'type': 'Entity', 'created_at': 1756300165516, 'updated_at': 1756300165516, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Primary contact email'})\n",
+      "({'id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'name': 'person', 'type': 'EntityType', 'created_at': 1759869236912, 'updated_at': 1759869236912, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'person'}, {'relationship_name': 'is_a', 'source_node_id': '29e771c8-4c3f-52de-9511-6b705878e130', 'target_node_id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'updated_at': '2025-10-07 20:33:55'}, {'id': '29e771c8-4c3f-52de-9511-6b705878e130', 'name': 'dr. emily carter', 'type': 'Entity', 'created_at': 1759869228456, 'updated_at': 1759869228456, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Senior Data Scientist with expertise in machine learning and predictive analytics.'})\n",
       "\n",
-      "({'id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'name': 'person', 'type': 'EntityType', 'created_at': 1756300165515, 'updated_at': 1756300165515, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'person'}, {'relationship_name': 'is_a', 'source_node_id': '29e771c8-4c3f-52de-9511-6b705878e130', 'target_node_id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'updated_at': '2025-08-27 13:03:24'}, {'id': '29e771c8-4c3f-52de-9511-6b705878e130', 'name': 'dr. emily carter', 'type': 'Entity', 'created_at': 1756299793321, 'updated_at': 1756299793321, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: emily.carter@example.com; phone: (555) 123-4567; profession: Senior Data Scientist; years_experience: 8; summary: Senior Data Scientist with over 8 years of experience in machine learning and predictive analytics'})\n",
+      "({'id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'name': 'person', 'type': 'EntityType', 'created_at': 1759869236912, 'updated_at': 1759869236912, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'person'}, {'relationship_name': 'is_a', 'source_node_id': 'a4777597-06c7-562c-bc44-56f74571a01a', 'target_node_id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'updated_at': '2025-10-07 20:33:57'}, {'id': 'a4777597-06c7-562c-bc44-56f74571a01a', 'name': 'david thompson', 'type': 'Entity', 'created_at': 1759869231360, 'updated_at': 1759869231360, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Creative Graphic Designer with over 8 years of experience in visual design and branding.'})\n",
       "\n",
-      "({'id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'name': 'person', 'type': 'EntityType', 'created_at': 1756300165515, 'updated_at': 1756300165515, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'person'}, {'relationship_name': 'is_a', 'source_node_id': '73ae630f-7b09-5dce-8c18-45d0a57b30f9', 'target_node_id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'updated_at': '2025-08-27 13:05:05'}, {'id': '73ae630f-7b09-5dce-8c18-45d0a57b30f9', 'name': 'michael rodriguez', 'type': 'Entity', 'created_at': 1756299890141, 'updated_at': 1756299890141, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: michael.rodriguez@example.com, phone: (555) 234-5678, summary: Data Scientist with background in machine learning and statistical modeling'})\n",
+      "({'id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'name': 'person', 'type': 'EntityType', 'created_at': 1759869236912, 'updated_at': 1759869236912, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'person'}, {'relationship_name': 'is_a', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'updated_at': '2025-10-07 20:34:03'}, {'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1759869236447, 'updated_at': 1759869236447, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist specializing in machine learning with 6 years of experience.'})\n",
       "\n",
-      "({'id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'name': 'person', 'type': 'EntityType', 'created_at': 1756300165515, 'updated_at': 1756300165515, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'person'}, {'relationship_name': 'is_a', 'source_node_id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'target_node_id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'updated_at': '2025-08-27 13:06:34'}, {'id': '4d8dda57-2681-5264-a2bd-e2ddfe66a785', 'name': 'sarah nguyen', 'type': 'Entity', 'created_at': 1756299984027, 'updated_at': 1756299984027, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: sarah.nguyen@example.com\\nphone: (555) 345-6789\\nsummary: Data Scientist specializing in machine learning with 6 years of experience'})\n",
+      "({'id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'name': 'person', 'type': 'EntityType', 'created_at': 1759869236912, 'updated_at': 1759869236912, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'person'}, {'relationship_name': 'is_a', 'source_node_id': '73ae630f-7b09-5dce-8c18-45d0a57b30f9', 'target_node_id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'updated_at': '2025-10-07 20:34:05'}, {'id': '73ae630f-7b09-5dce-8c18-45d0a57b30f9', 'name': 'michael rodriguez', 'type': 'Entity', 'created_at': 1759869236913, 'updated_at': 1759869236913, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Data Scientist with a strong background in machine learning and statistical modeling.'})\n",
       "\n",
-      "({'id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'name': 'person', 'type': 'EntityType', 'created_at': 1756300165515, 'updated_at': 1756300165515, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'person'}, {'relationship_name': 'is_a', 'source_node_id': 'a4777597-06c7-562c-bc44-56f74571a01a', 'target_node_id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'updated_at': '2025-08-27 13:07:50'}, {'id': 'a4777597-06c7-562c-bc44-56f74571a01a', 'name': 'david thompson', 'type': 'Entity', 'created_at': 1756300059090, 'updated_at': 1756300059090, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'summary: Creative Graphic Designer with over 8 years of experience in visual design and branding'})\n",
-      "\n",
-      "({'id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'name': 'person', 'type': 'EntityType', 'created_at': 1756300165515, 'updated_at': 1756300165515, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'person'}, {'relationship_name': 'is_a', 'source_node_id': '36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932', 'target_node_id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'updated_at': '2025-08-27 13:09:40'}, {'id': '36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932', 'name': 'jessica miller', 'type': 'Entity', 'created_at': 1756300165515, 'updated_at': 1756300165515, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Experienced Sales Manager with a strong track record in driving sales growth and building high-performing teams.'})\n",
-      "\n",
-      "({'id': 'e308d782-2a18-5ace-b0e8-236c7c3b4db4', 'name': 'team', 'type': 'EntityType', 'created_at': 1756300245016, 'updated_at': 1756300245016, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'team'}, {'relationship_name': 'is_a', 'source_node_id': '402e2e8b-9150-5ee8-b71b-f9b91f9699e1', 'target_node_id': 'e308d782-2a18-5ace-b0e8-236c7c3b4db4', 'updated_at': '2025-08-27 13:11:09'}, {'id': '402e2e8b-9150-5ee8-b71b-f9b91f9699e1', 'name': 'analytics team', 'type': 'Entity', 'created_at': 1756300245016, 'updated_at': 1756300245016, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Dynamic analytics team at TechNova Solutions.'})\n",
-      "\n",
-      "({'id': 'ceab6411-7a0b-5c82-a2a2-bbfab015fe03', 'name': 'contact', 'type': 'EntityType', 'created_at': 1756300059091, 'updated_at': 1756300059091, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'contact'}, {'relationship_name': 'is_a', 'source_node_id': '282e7e92-e3d5-5a27-96fd-f145d6ebf7ec', 'target_node_id': 'ceab6411-7a0b-5c82-a2a2-bbfab015fe03', 'updated_at': '2025-08-27 13:07:50'}, {'id': '282e7e92-e3d5-5a27-96fd-f145d6ebf7ec', 'name': 'david.thompson@example.com', 'type': 'Entity', 'created_at': 1756300059091, 'updated_at': 1756300059091, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'email: david.thompson@example.com'})\n",
-      "\n",
-      "({'id': 'ceab6411-7a0b-5c82-a2a2-bbfab015fe03', 'name': 'contact', 'type': 'EntityType', 'created_at': 1756300059091, 'updated_at': 1756300059091, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'contact'}, {'relationship_name': 'is_a', 'source_node_id': 'f2daec66-8503-57ae-8ceb-b590a0593eeb', 'target_node_id': 'ceab6411-7a0b-5c82-a2a2-bbfab015fe03', 'updated_at': '2025-08-27 13:07:50'}, {'id': 'f2daec66-8503-57ae-8ceb-b590a0593eeb', 'name': '(555) 456-7890', 'type': 'Entity', 'created_at': 1756300059092, 'updated_at': 1756300059092, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'phone: (555) 456-7890'})\n",
+      "({'id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'name': 'person', 'type': 'EntityType', 'created_at': 1759869236912, 'updated_at': 1759869236912, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'person'}, {'relationship_name': 'is_a', 'source_node_id': '36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932', 'target_node_id': 'd072ba0f-e1a9-58bf-9974-e1802adc8134', 'updated_at': '2025-10-07 20:34:03'}, {'id': '36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932', 'name': 'jessica miller', 'type': 'Entity', 'created_at': 1759869237035, 'updated_at': 1759869237035, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'belongs_to_set': None, 'description': 'Experienced Sales Manager with a strong track record in driving sales growth and building high-performing teams.'})\n",
       "\n"
      ]
     }
@@ -1806,7 +1400,19 @@
    "execution_count": null,
    "id": "d42b3245",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
+      "\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
+      "\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n",
+      "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
+     ]
+    }
+   ],
    "source": [
     "# Only exit in interactive mode, not during GitHub Actions\n",
     "import os\n",
@@ -1845,7 +1451,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.7"
+   "version": "3.10.11"
   }
  },
  "nbformat": 4,
diff --git a/notebooks/cognee_multimedia_demo.ipynb b/notebooks/cognee_multimedia_demo.ipynb
index 72342250b..608e11956 100644
--- a/notebooks/cognee_multimedia_demo.ipynb
+++ b/notebooks/cognee_multimedia_demo.ipynb
@@ -22,7 +22,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2025-06-30T11:54:44.613431Z",
@@ -57,7 +57,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2025-06-30T11:54:46.739157Z",
@@ -97,6 +97,38 @@
     "# os.environ[\"DB_PASSWORD\"]=\"cognee\""
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[2m2025-10-07T20:37:13.488510\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted old log file: /Users/daulet/Desktop/dev/cognee-claude/logs/2025-10-07_21-16-23.log\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:37:14.172414\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLogging initialized           \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m \u001b[36mcognee_version\u001b[0m=\u001b[35m0.3.5-local\u001b[0m \u001b[36mdatabase_path\u001b[0m=\u001b[35m/Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m \u001b[36mgraph_database_name\u001b[0m=\u001b[35m\u001b[0m \u001b[36mos_info\u001b[0m=\u001b[35m'Darwin 24.5.0 (Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:43 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8132)'\u001b[0m \u001b[36mpython_version\u001b[0m=\u001b[35m3.10.11\u001b[0m \u001b[36mrelational_config\u001b[0m=\u001b[35mcognee_db\u001b[0m \u001b[36mstructlog_version\u001b[0m=\u001b[35m25.4.0\u001b[0m \u001b[36mvector_config\u001b[0m=\u001b[35mlancedb\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:37:14.172932\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase storage: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "/Users/daulet/Desktop/dev/cognee-claude/.venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.3.5-local\n"
+     ]
+    }
+   ],
+   "source": [
+    "import cognee\n",
+    "print(cognee.__version__)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -114,31 +146,24 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "\u001b[2m2025-08-27T14:33:41.256195\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted old log file: /Users/daulet/Desktop/dev/cognee-claude/logs/2025-08-27_14-00-27.log\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
-      "/Users/daulet/Desktop/dev/cognee-claude/.venv/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "\u001b[2m2025-10-07T20:37:20.743332\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLoaded JSON extension         \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:42.133224\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLogging initialized           \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m \u001b[36mcognee_version\u001b[0m=\u001b[35m0.2.4-local\u001b[0m \u001b[36mdatabase_path\u001b[0m=\u001b[35m/Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m \u001b[36mgraph_database_name\u001b[0m=\u001b[35m\u001b[0m \u001b[36mos_info\u001b[0m=\u001b[35m'Darwin 24.5.0 (Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:43 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8132)'\u001b[0m \u001b[36mpython_version\u001b[0m=\u001b[35m3.12.7\u001b[0m \u001b[36mrelational_config\u001b[0m=\u001b[35mcognee_db\u001b[0m \u001b[36mstructlog_version\u001b[0m=\u001b[35m25.4.0\u001b[0m \u001b[36mvector_config\u001b[0m=\u001b[35mlancedb\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:20.776490\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted Kuzu database files at /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases/cognee_graph_kuzu\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:42.133667\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase storage: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:23.387773\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase deleted successfully.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:43.785214\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted Kuzu database files at /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases/cognee_graph_kuzu\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\u001b[1mStorage manager absolute path: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_cache\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:44.215920\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase deleted successfully.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\u001b[1mDeleting cache...             \u001b[0m\n",
       "\n",
-      "\u001b[1mLangfuse client is disabled since no public_key was provided as a parameter or environment variable 'LANGFUSE_PUBLIC_KEY'. See our docs: https://langfuse.com/docs/sdk/python/low-level-sdk#initialize-client\u001b[0m\n",
-      "\u001b[92m15:33:44 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n"
+      "\u001b[1m✓ Cache deleted successfully! \u001b[0m\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "User 37ea34fa-cae7-4bea-8cb3-1ba234688771 has registered.\n"
+      "User 03f552c1-331f-40b2-a99b-b3b05aa93e0d has registered.\n"
      ]
     },
     {
@@ -148,164 +173,131 @@
       "\n",
       "\u001b[1mEmbeddingRateLimiter initialized: enabled=False, requests_limit=60, interval_seconds=60\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:50.440270\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `017311b3-90e5-53ce-9974-00c4d9551248`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:24.691142\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `e16895e4-38f6-5ad7-a969-cd1629861b40`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:50.690756\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:24.691670\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:50.996600\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:24.692087\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:51.287352\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: pypdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:24.693388\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `e16895e4-38f6-5ad7-a969-cd1629861b40`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:51.287759\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: text_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:24.693668\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:51.288078\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: image_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:24.694024\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:51.288341\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: audio_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:24.708303\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: pypdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:51.288576\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: unstructured_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
-      "\u001b[92m15:33:52 - LiteLLM:INFO\u001b[0m: utils.py:1274 - Wrapper: Completed Call, calling success_handler\n",
+      "\u001b[2m2025-10-07T20:37:24.708776\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: text_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mWrapper: Completed Call, calling success_handler\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:24.709084\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: image_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:52.455447\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:24.709426\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: audio_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:52.599686\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:24.709654\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: unstructured_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:52.806593\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `017311b3-90e5-53ce-9974-00c4d9551248`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:24.709898\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: advanced_pdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:53.075106\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `017311b3-90e5-53ce-9974-00c4d9551248`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.420233\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:53.209912\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.420796\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:53.355890\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m15:33:53 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:37:28.421255\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `e16895e4-38f6-5ad7-a969-cd1629861b40`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m15:33:57 - LiteLLM:INFO\u001b[0m: utils.py:1274 - Wrapper: Completed Call, calling success_handler\n",
+      "\u001b[2m2025-10-07T20:37:28.423491\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1mWrapper: Completed Call, calling success_handler\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.423881\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:57.407561\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.424259\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `e16895e4-38f6-5ad7-a969-cd1629861b40`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:57.560808\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.434168\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:57.713507\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `017311b3-90e5-53ce-9974-00c4d9551248`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.453069\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `453ce944-eb27-567c-9918-0d44d1614f97`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:57.897060\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.453489\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:57.938027\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `9bd0d908-8e9e-5780-b4c2-09fc8d471f1b`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.453823\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:58.093101\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.454419\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `453ce944-eb27-567c-9918-0d44d1614f97`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:58.255165\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.454689\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:58.428623\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.454948\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:33:58.588682\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m15:33:58 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:37:28.462413\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.466745\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:19.706892\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.470294\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:19.707703\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'programmer' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:28.476006\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:19.708083\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'object' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:32.030103\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLoaded JSON extension         \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:19.708440\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'light bulb' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:32.065148\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:19.708802\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:32.065868\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'programmer' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:19.709129\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'hardware problem' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:32.066315\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'object' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:19.709475\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'how many programmers does it take to change a light bulb? none, thats a hardware problem.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:32.066713\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'light bulb' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:24.553989\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m15:34:24 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:37:32.067064\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:32.067410\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'hardware problem' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:32.883579\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:32.202761\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'profession' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:35.680233\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:32.203355\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'programmers' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:35.825933\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:32.203785\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'hardware' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:35.975352\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:32.204225\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'light bulb' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:36.126720\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:32.204544\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:36.275404\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:32.204964\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'humor' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:36.424984\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:34.265785\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:36.576258\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `9bd0d908-8e9e-5780-b4c2-09fc8d471f1b`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:35.003525\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:36.754472\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `9bd0d908-8e9e-5780-b4c2-09fc8d471f1b`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:35.952187\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:36.912219\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:35.970171\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:37.053036\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:38.024476\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:37.220157\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:38.025311\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:34:37.388094\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m15:34:37 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:37:38.025564\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:38.025803\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:35:00.010321\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:38.026065\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:35:00.012394\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'programmers' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:38.026413\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:35:00.012794\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'object' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:38.026663\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `453ce944-eb27-567c-9918-0d44d1614f97`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:35:00.013111\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'light bulb' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:38.680393\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:35:00.013378\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:38.680986\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:35:00.013598\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'hardware problem' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:38.681355\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:35:00.013914\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'joke' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:38.681647\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:35:00.014215\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'programmer joke' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:38.681917\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:35:02.040520\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m15:35:02 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:37:38.682229\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T14:35:11.589828\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T14:35:14.446614\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T14:35:14.622281\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T14:35:14.820192\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T14:35:15.004173\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T14:35:15.518803\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T14:35:15.756519\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T14:35:15.978364\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `9bd0d908-8e9e-5780-b4c2-09fc8d471f1b`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n"
+      "\u001b[2m2025-10-07T20:37:38.682567\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `453ce944-eb27-567c-9918-0d44d1614f97`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "{UUID('a08926db-6319-5cd9-adc9-2cf9dfbc75e0'): PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('69b78d3d-4d27-5d9f-918f-57e77b3cb10a'), dataset_id=UUID('a08926db-6319-5cd9-adc9-2cf9dfbc75e0'), dataset_name='main_dataset', payload=None, data_ingestion_info=[{'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('69b78d3d-4d27-5d9f-918f-57e77b3cb10a'), dataset_id=UUID('a08926db-6319-5cd9-adc9-2cf9dfbc75e0'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('17b5c469-a8ce-5347-bea5-ab3dba767d13')}, {'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('69b78d3d-4d27-5d9f-918f-57e77b3cb10a'), dataset_id=UUID('a08926db-6319-5cd9-adc9-2cf9dfbc75e0'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('5b1e3c7e-d837-5704-a3b3-53abdda3a84f')}])}"
+       "{UUID('8f486d81-4723-5f3d-b37b-5e27d9967d33'): PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('1c237436-d3eb-5408-874d-91647cf2dcef'), dataset_id=UUID('8f486d81-4723-5f3d-b37b-5e27d9967d33'), dataset_name='main_dataset', payload=None, data_ingestion_info=[{'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('1c237436-d3eb-5408-874d-91647cf2dcef'), dataset_id=UUID('8f486d81-4723-5f3d-b37b-5e27d9967d33'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('56c22102-965d-592e-958c-c1ebebf0008f')}, {'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('1c237436-d3eb-5408-874d-91647cf2dcef'), dataset_id=UUID('8f486d81-4723-5f3d-b37b-5e27d9967d33'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('e26acfac-f1c2-5d9d-b95a-e970a75aedde')}])}"
       ]
      },
      "execution_count": 4,
@@ -349,23 +341,29 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "\u001b[2m2025-08-27T14:36:09.273837\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting completion generation for query: 'What is in the multimedia files?'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:42.668682\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting summary retrieval for query: 'What is in the multimedia files?'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
       "\n",
-      "\u001b[2m2025-08-27T14:36:09.275355\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting summary retrieval for query: 'What is in the multimedia files?'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:42.933137\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mFound 2 summaries from vector search\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:36:09.691101\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mFound 2 summaries from vector search\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:42.933995\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReturning 2 summary payloads  \u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:36:09.691827\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReturning 2 summary payloads  \u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:37:42.934301\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting completion generation for query: 'What is in the multimedia files?'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T14:36:09.692207\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReturning context with 2 item(s)\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n"
+      "\u001b[2m2025-10-07T20:37:42.934604\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReturning context with 2 item(s)\u001b[0m [\u001b[0m\u001b[1m\u001b[34mSummariesRetriever\u001b[0m]\u001b[0m\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'id': 'facab42e-12fc-557e-aaf4-09c02ae1cd4f', 'created_at': 1756305273061, 'updated_at': 1756305273061, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': \"Programmers won't change a light bulb — it's considered a hardware issue.\"}\n",
-      "{'id': '958f2bc9-060b-5500-b14a-19b300cc99aa', 'created_at': 1756305311791, 'updated_at': 1756305311791, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'One-line programmer joke: changing a light bulb is labeled a hardware issue.'}\n"
+      "{'id': '766ac5d6-1a81-530e-a934-61e2bf505d9b', 'created_at': 1759869455990, 'updated_at': 1759869455990, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': 'A humorous take on programmers and light bulbs.'}\n",
+      "{'id': '2862798a-0dfc-5994-a3ca-9f4329f42f06', 'created_at': 1759869455989, 'updated_at': 1759869455989, 'ontology_valid': False, 'version': 1, 'topological_rank': 0, 'type': 'IndexSchema', 'text': \"Programmers won't change a light bulb.\"}\n"
      ]
     }
    ],
@@ -429,7 +427,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.7"
+   "version": "3.10.11"
   }
  },
  "nbformat": 4,
diff --git a/notebooks/cognee_simple_demo.ipynb b/notebooks/cognee_simple_demo.ipynb
index 6ca42ada5..161e03d4b 100644
--- a/notebooks/cognee_simple_demo.ipynb
+++ b/notebooks/cognee_simple_demo.ipynb
@@ -79,580 +79,246 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "\u001b[2m2025-08-27T13:34:14.905059\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted old log file: /Users/daulet/Desktop/dev/cognee-claude/logs/2025-08-26_12-44-42.log\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
-      "/Users/daulet/Desktop/dev/cognee-claude/.venv/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "\u001b[2m2025-10-07T20:38:23.321871\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted old log file: /Users/daulet/Desktop/dev/cognee-claude/logs/2025-10-07_21-16-35.log\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:15.858104\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLogging initialized           \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m \u001b[36mcognee_version\u001b[0m=\u001b[35m0.2.4-local\u001b[0m \u001b[36mdatabase_path\u001b[0m=\u001b[35m/Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m \u001b[36mgraph_database_name\u001b[0m=\u001b[35m\u001b[0m \u001b[36mos_info\u001b[0m=\u001b[35m'Darwin 24.5.0 (Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:43 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8132)'\u001b[0m \u001b[36mpython_version\u001b[0m=\u001b[35m3.12.7\u001b[0m \u001b[36mrelational_config\u001b[0m=\u001b[35mcognee_db\u001b[0m \u001b[36mstructlog_version\u001b[0m=\u001b[35m25.4.0\u001b[0m \u001b[36mvector_config\u001b[0m=\u001b[35mlancedb\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:23.924664\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLogging initialized           \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m \u001b[36mcognee_version\u001b[0m=\u001b[35m0.3.5-local\u001b[0m \u001b[36mdatabase_path\u001b[0m=\u001b[35m/Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m \u001b[36mgraph_database_name\u001b[0m=\u001b[35m\u001b[0m \u001b[36mos_info\u001b[0m=\u001b[35m'Darwin 24.5.0 (Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:43 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8132)'\u001b[0m \u001b[36mpython_version\u001b[0m=\u001b[35m3.10.11\u001b[0m \u001b[36mrelational_config\u001b[0m=\u001b[35mcognee_db\u001b[0m \u001b[36mstructlog_version\u001b[0m=\u001b[35m25.4.0\u001b[0m \u001b[36mvector_config\u001b[0m=\u001b[35mlancedb\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:15.859638\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase storage: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[1mLangfuse client is disabled since no public_key was provided as a parameter or environment variable 'LANGFUSE_PUBLIC_KEY'. See our docs: https://langfuse.com/docs/sdk/python/low-level-sdk#initialize-client\u001b[0m\n",
-      "\u001b[92m14:34:18 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:23.925152\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase storage: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "/Users/daulet/Desktop/dev/cognee-claude/.venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.3.5-local\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
       "\n",
       "\u001b[1mEmbeddingRateLimiter initialized: enabled=False, requests_limit=60, interval_seconds=60\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:22.954992\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `bb1e12db-8d3f-5e80-8615-2444eda4b32a`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.824653\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `e16895e4-38f6-5ad7-a969-cd1629861b40`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:23.160900\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.825175\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:23.335242\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.825559\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:23.516399\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: pypdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.834754\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: pypdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:23.517356\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: text_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.835421\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: text_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:23.518011\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: image_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.835697\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: image_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:23.518486\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: audio_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.835966\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: audio_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:23.519037\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: unstructured_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.836157\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: unstructured_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:23.536911\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.836754\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: advanced_pdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:23.685341\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.847087\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:23.836303\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `bb1e12db-8d3f-5e80-8615-2444eda4b32a`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.847599\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:24.058213\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.847894\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `e16895e4-38f6-5ad7-a969-cd1629861b40`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:24.084248\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `52948913-bf39-51ee-a535-e4f140f34c10`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.967450\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mJSON extension already loaded or unavailable: Binder exception: Extension: JSON is already loaded. You can check loaded extensions by `CALL SHOW_LOADED_EXTENSIONS() RETURN *`.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:24.232775\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.980303\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:24.378181\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.998286\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `453ce944-eb27-567c-9918-0d44d1614f97`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:24.555749\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:30.998936\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:34:24.803351\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:34:24 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:38:30.999638\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:34:24 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:38:31.006879\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:34:24 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:38:31.119544\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:34:24 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:38:51.668159\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:34:24 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:38:51.669164\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'alice' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:34:24 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:38:51.669470\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'white rabbit' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:34:24 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:38:51.669777\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'animal' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:34:24 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:38:51.670086\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'dinah' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:34:24 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
+      "\u001b[2m2025-10-07T20:38:51.670369\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'location' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.670667\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'rabbit-hole' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.974856\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.670972\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'garden' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.976689\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'alice' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.671244\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'object' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.976989\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'animal' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.671450\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'table' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.977311\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'white rabbit' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.671650\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'golden key' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.977608\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'dinah' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.671857\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'bottle' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.977842\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'location' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.672094\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cake' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.978119\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'rabbit hole' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.672398\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mouse' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.978445\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tunnel or well' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.672607\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'dodo' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.978688\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'heap of sticks and dry leaves' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.672847\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'lory' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.979010\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'long low hall' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.673136\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'eaglet' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.979218\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'object' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.673399\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'duck' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.979434\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'three legged glass table' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.673634\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'historical figure' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.979726\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tiny golden key' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.673871\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'william the conqueror' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.979974\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'little door' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.674120\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mary ann' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.980178\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'small passage' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.674384\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'duchess' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.980378\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'lovely garden' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.674682\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'creature' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.980559\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'jar labeled orange marmalade' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.674931\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caterpillar' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.980758\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cupboard' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.675153\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'rabbit' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.980944\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'bottle labeled drink me' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.675376\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'bill' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.981181\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'small glass box' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.675611\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'plant' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.981405\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cake labeled eat me' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.675837\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mushroom' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.981672\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pool of tears' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.676060\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'father william' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.981921\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'white kid gloves and fan' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.676333\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'character' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.982174\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'bookchapter' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.676573\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pigeon' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.982434\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chapter i down the rabbit hole' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.676801\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'baby' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.982656\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chapter ii the pool of tears' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.677018\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cheshire cat' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.983007\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mouse' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.677242\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'hatter' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.983274\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'duck' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.677490\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'march hare' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.983483\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'dodo' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.677694\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'queen' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.983677\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'lory' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.677922\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cook' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.983917\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'eaglet' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.678148\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.984157\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'magpie' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.678396\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'may' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.984380\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'canary' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.678677\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the cat' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.984576\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'old crab' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.678911\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the dormouse' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.984798\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'young crab' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.679113\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the queen of hearts' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.985030\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'animalclass' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.679341\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the king of hearts' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.985270\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cats' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.679587\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the knave of hearts' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.985465\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'dogs' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.679917\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the rose tree' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.985698\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'shore' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.680113\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'event' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.985875\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'w. rabbit house' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.680347\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the mad tea party' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.986089\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'fan' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.680632\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'king' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.986292\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'white kid gloves' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.681429\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mock turtle' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.986527\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'bottle (drink me)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.681702\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'gryphon' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.986754\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'thimble' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.681931\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'soldiers' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.986962\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'comfits' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.682200\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'gardener_1' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.987297\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'event' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.682379\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'gardener_2' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.987508\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caucus-race' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.682699\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'gardener_3' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.987735\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'grew large event' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.683245\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tortoise' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.988057\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'creature' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.683560\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'lizards' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.988461\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'magic bottle' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.683846\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'food' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.988654\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'size-changing cake' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.684025\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tarts' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.988869\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pebbles' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.684355\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'dance' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.989079\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mushroom' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.684671\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'lobster quadrille' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.989289\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caterpillar' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.684888\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'subject' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.989498\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'hookah' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.685135\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'seaography' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.989699\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'bill (lizard)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.685394\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'arithmetic' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.989916\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'guinea-pigs' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.685715\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mystery' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.990178\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pat' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.685998\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.990390\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mary ann' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.686239\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'court' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.990541\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'place' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.686484\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'guinea pig' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.990742\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'rabbit house' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.686688\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'lizard' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.990894\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'window' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.686886\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'march 14' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.991048\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'door' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.687125\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'march 15' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.991246\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chimney' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.687426\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'march 16' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.991431\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cucumber-frame' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.687861\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'place' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.991636\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'wood' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.688321\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'wonderland' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.991856\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'puppy' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.688615\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sister' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.992038\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'father william' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.688914\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'farm-yard' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.992222\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.689141\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'child-life' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.992402\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'size change' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.689345\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'simple_joys' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.992893\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pigeon' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:51.689662\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'simple_sorrows' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.993054\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'serpent' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:38:55.033467\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.993213\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'trees' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:39:03.406344\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.993435\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'little house' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:39:07.113087\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.993576\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'fish-footman' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:39:07.113738\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.993834\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'frog-footman' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:39:07.114015\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.994053\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'duchess' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:39:07.114579\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.994264\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cook' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:39:07.114971\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.994443\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'baby' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:39:07.115220\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:35:55.994661\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pig' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.994797\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cheshire cat' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.994960\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'kitchen' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.995114\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cauldron' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.995283\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'soup' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.995444\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pepper' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.995637\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'plate' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.995924\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'frying-pan' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.996079\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'invitation letter' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.996298\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'queen' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.996443\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'hatter' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.996602\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'march hare' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.996794\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'game' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.996993\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'croquet' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.997436\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the cat' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.997651\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the dormouse' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.997898\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'a mad tea-party' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.998205\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'table' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.998409\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the hatters watch' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.998581\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'house of the march hare' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.998819\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'a rose-tree' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.998980\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'five' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.999133\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'two' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.999302\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'seven' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.999465\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'group' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:55.999749\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'soldiers' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.000078\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'courtiers' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.000273\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'royal children' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.001132\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'knave of hearts' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.002873\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the king of hearts' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.003453\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the queen of hearts' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.004815\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'treacle-well' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.005347\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'elsie' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.005583\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'lacie' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.005904\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tillie' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.006224\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'riddle: why is a raven like a writing-desk?' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.006483\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'song: twinkle twinkle little bat' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.006698\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tea-time' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.007096\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'the king' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.007449\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'executioner' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.008948\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'gryphon' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.009396\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mock turtle' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.009604\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'croquet game' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.009761\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'croquet ground' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.010011\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'hedgehog' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.010238\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'flamingo' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.010525\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'rose-tree' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.010795\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'flower-pot' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.011185\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'players' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.011425\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mock turtle soup' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.011802\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'old turtle (tortoise)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.012966\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'bill the lizard' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.014629\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'lobster' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.015124\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'whiting' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.015383\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'snail' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.015702\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'porpoise' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.015898\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'owl' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.016462\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'panther' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.017210\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sea' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.017407\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sea-shore' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.017920\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'court of hearts' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.018187\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'lobster quadrille (dance)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.019379\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'creativework' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.020269\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'beautiful soup' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.021436\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'whiting song' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.022224\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'school (sea-school)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.022613\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'reeling and writhing' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.022812\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'ambition' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.023185\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'distraction' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.023469\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'uglification' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.023674\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'derision' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.023904\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mystery (ancient and modern)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.024157\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'seaography' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.024376\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'drawling' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.024600\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'stretching' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.024992\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'fainting in coils' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.025219\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'laughing' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.025502\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'grief' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.025949\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'conger eel (drawling-master)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.026243\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'old crab (classics master)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.026692\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tarts' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.026920\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pencil' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.027897\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'slate' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.028631\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'duchesss cook' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.028848\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'lizard (bill)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.029560\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'guinea-pigs' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.030437\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'organization' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.030900\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'jury' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.031211\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'trial of the knave' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.031414\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'document' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.031563\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'parchment scroll' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.031771\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'trumpet' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.031975\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'teacup' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.032145\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'bread-and-butter' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.032348\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pepper-box' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.032520\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'inkstand' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.032767\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'canvas bag' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.033132\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'jury-box' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.034834\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'alices dream' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.036198\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.037172\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'fourteenth of march' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.037973\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'fifteenth of march' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.038237\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sixteenth of march' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.038606\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'she' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.038879\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'little sister' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.039022\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'wonderland' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.039194\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'dull reality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.039400\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'plant' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.039578\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'grass' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.039741\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pool' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.039913\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'reeds' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.040074\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'rattling teacups' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.040285\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tinkling sheep-bells' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.040468\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'shepherd boy' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.040662\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'other queer noises' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.040836\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'busy farm-yard' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.041105\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cattle' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.041323\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'grown woman' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.042019\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'simple and loving heart' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.042329\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'other little children' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.042583\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'strange tale' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.042824\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'dream of wonderland' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.043010\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'simple sorrows' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.043173\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'simple joys' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.043331\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'child-life' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:35:56.043505\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'happy summer days' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:36:02.674965\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:36:02 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:36:02 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:36:02 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:36:02 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:36:02 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:36:02 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:36:02 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:36:02 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\u001b[92m14:36:02 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:36:16.723969\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:36:24.505751\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:36:24.656760\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:36:24.853916\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:36:24.999416\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:36:25.182065\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:36:25.379190\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
-      "\n",
-      "\u001b[2m2025-08-27T13:36:25.534779\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `52948913-bf39-51ee-a535-e4f140f34c10`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n"
+      "\u001b[2m2025-10-07T20:39:07.115479\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `453ce944-eb27-567c-9918-0d44d1614f97`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "{UUID('241b64d6-f023-5b87-9a8f-87056f0a442c'): PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('1cde937f-ae7a-5151-a20c-dc3567bee0a9'), dataset_id=UUID('241b64d6-f023-5b87-9a8f-87056f0a442c'), dataset_name='main_dataset', payload=None, data_ingestion_info=[{'run_info': PipelineRunAlreadyCompleted(status='PipelineRunAlreadyCompleted', pipeline_run_id=UUID('1cde937f-ae7a-5151-a20c-dc3567bee0a9'), dataset_id=UUID('241b64d6-f023-5b87-9a8f-87056f0a442c'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('692741cd-46e5-5988-85e9-f3901d104b7e')}, {'run_info': PipelineRunAlreadyCompleted(status='PipelineRunAlreadyCompleted', pipeline_run_id=UUID('1cde937f-ae7a-5151-a20c-dc3567bee0a9'), dataset_id=UUID('241b64d6-f023-5b87-9a8f-87056f0a442c'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('899de74a-1bef-5afd-a478-1ea944503514')}, {'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('1cde937f-ae7a-5151-a20c-dc3567bee0a9'), dataset_id=UUID('241b64d6-f023-5b87-9a8f-87056f0a442c'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('6a0c7501-47bc-5632-b79c-3343d8a0b2a2')}])}"
+       "{UUID('8f486d81-4723-5f3d-b37b-5e27d9967d33'): PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('1c237436-d3eb-5408-874d-91647cf2dcef'), dataset_id=UUID('8f486d81-4723-5f3d-b37b-5e27d9967d33'), dataset_name='main_dataset', payload=None, data_ingestion_info=[{'run_info': PipelineRunCompleted(status='PipelineRunCompleted', pipeline_run_id=UUID('1c237436-d3eb-5408-874d-91647cf2dcef'), dataset_id=UUID('8f486d81-4723-5f3d-b37b-5e27d9967d33'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('3ad0b58b-2b39-5bf8-97de-4db67bd2555c')}, {'run_info': PipelineRunAlreadyCompleted(status='PipelineRunAlreadyCompleted', pipeline_run_id=UUID('1c237436-d3eb-5408-874d-91647cf2dcef'), dataset_id=UUID('8f486d81-4723-5f3d-b37b-5e27d9967d33'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('56c22102-965d-592e-958c-c1ebebf0008f')}, {'run_info': PipelineRunAlreadyCompleted(status='PipelineRunAlreadyCompleted', pipeline_run_id=UUID('1c237436-d3eb-5408-874d-91647cf2dcef'), dataset_id=UUID('8f486d81-4723-5f3d-b37b-5e27d9967d33'), dataset_name='main_dataset', payload=None, data_ingestion_info=None), 'data_id': UUID('e26acfac-f1c2-5d9d-b95a-e970a75aedde')}])}"
       ]
      },
      "execution_count": 3,
@@ -662,6 +328,7 @@
    ],
    "source": [
     "import cognee\n",
+    "print(cognee.__version__)\n",
     "await cognee.add(file_path)\n",
     "await cognee.cognify()"
    ]
@@ -685,20 +352,15 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "\u001b[2m2025-08-27T13:36:30.994342\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph projection completed: 239 nodes, 745 edges in 0.01s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mCogneeGraph\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:39:07.164471\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph projection completed: 110 nodes, 292 edges in 0.01s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mCogneeGraph\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:36:31.598044\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mVector collection retrieval completed: Retrieved distances from 6 collections in 0.04s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
-      "\u001b[92m14:36:31 - LiteLLM:INFO\u001b[0m: utils.py:3341 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\n"
+      "\u001b[2m2025-10-07T20:39:07.474073\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mVector collection retrieval completed: Retrieved distances from 6 collections in 0.09s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "['Acknowledged.']"
+       "['1. Alice  \\n2. White Rabbit  \\n3. March Hare  \\n4. Hatter  \\n5. Cheshire Cat  \\n6. Queen of Hearts  \\n7. Knave of Hearts  \\n8. Dormouse']"
       ]
      },
      "execution_count": 4,
@@ -712,7 +374,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "883ce50d2d9dc584",
    "metadata": {},
    "outputs": [
@@ -720,44 +382,19 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:01 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:01 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:01 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:01 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:01 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:02 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:03 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:03 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:03 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:17:05 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:17:05 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m"
+      "\n",
+      "\u001b[2m2025-10-07T20:39:36.551739\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph projection completed: 110 nodes, 292 edges in 0.01s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mCogneeGraph\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:39:36.896038\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mVector collection retrieval completed: Retrieved distances from 6 collections in 0.09s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "[\"Alice ended up in Wonderland by following a curious White Rabbit that she encountered while sitting on a riverbank. The Rabbit muttered about being late and carried a watch, piquing Alice's curiosity. She followed it down a rabbit hole, which led her to a fantastical world.\"]"
+       "['Alice ended up in Wonderland by following a hurried White Rabbit down a rabbit-hole after feeling bored and drowsy.']"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -768,7 +405,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "id": "677e1bc52aa078b6",
    "metadata": {},
    "outputs": [
@@ -776,44 +413,19 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:07 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
-      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:17:07 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
-      "\u001b[1m\n",
-      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:17:08 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:17:08 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
-      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m"
+      "\n",
+      "\u001b[2m2025-10-07T20:39:43.171619\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph projection completed: 110 nodes, 292 edges in 0.02s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mCogneeGraph\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:39:43.468210\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mVector collection retrieval completed: Retrieved distances from 6 collections in 0.08s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "['Alice is portrayed as a curious and adventurous girl who explores Wonderland. She often questions her identity and the world around her, showing a blend of innocence and boldness. Alice displays a willingness to engage with bizarre situations and characters, while also being contemplative about her experiences.']"
+       "[\"Alice is described as a curious girl who exhibits a desire for adventure and exploration. She is imaginative, pondering various whimsical questions and thoughts as she navigates the oddities of Wonderland. Her personality shows signs of being thoughtful and reflective, often giving herself advice, though she doesn't always follow it. Despite her adventures and the surreal situations she encounters, she maintains a sense of bravery and a degree of confidence in her interactions with the fantastical characters she meets.\"]"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -832,7 +444,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "id": "6effdae590b795d3",
    "metadata": {},
    "outputs": [
@@ -841,9 +453,9 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "\u001b[2m2025-08-27T13:36:40.283583\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph visualization saved as /Users/daulet/graph_visualization.html\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\u001b[2m2025-10-07T20:39:50.413314\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph visualization saved as /Users/daulet/graph_visualization.html\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
       "\n",
-      "\u001b[2m2025-08-27T13:36:40.284941\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mThe HTML file has been stored on your home directory! Navigate there with cd ~\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
+      "\u001b[2m2025-10-07T20:39:50.413846\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mThe HTML file has been stored on your home directory! Navigate there with cd ~\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
      ]
     },
     {
@@ -861,7 +473,7 @@
        "True"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -932,7 +544,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.7"
+   "version": "3.10.11"
   }
  },
  "nbformat": 4,
diff --git a/notebooks/ontology_demo.ipynb b/notebooks/ontology_demo.ipynb
index ef4a046b8..17d7feb28 100644
--- a/notebooks/ontology_demo.ipynb
+++ b/notebooks/ontology_demo.ipynb
@@ -36,36 +36,61 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "8cf7ba29f9a150af",
    "metadata": {},
+   "outputs": [],
    "source": [
     "# Install required package\n",
     "# !pip install cognee"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": 1,
    "id": "abb86851",
    "metadata": {},
+   "outputs": [],
    "source": [
     "import os\n",
     "\n",
     "# Set up OpenAI API key (required for Cognee's LLM functionality)\n",
     "if \"LLM_API_KEY\" not in os.environ:\n",
     "    os.environ[\"LLM_API_KEY\"] = \"your-api-key-here\"  # Replace with your API key"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": 2,
    "id": "d825d126b3a0ec26",
    "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[2m2025-10-07T20:40:15.192965\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted old log file: /Users/daulet/Desktop/dev/cognee-claude/logs/2025-10-07_21-25-04.log\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:15.894155\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLogging initialized           \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m \u001b[36mcognee_version\u001b[0m=\u001b[35m0.3.5-local\u001b[0m \u001b[36mdatabase_path\u001b[0m=\u001b[35m/Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m \u001b[36mgraph_database_name\u001b[0m=\u001b[35m\u001b[0m \u001b[36mos_info\u001b[0m=\u001b[35m'Darwin 24.5.0 (Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:43 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8132)'\u001b[0m \u001b[36mpython_version\u001b[0m=\u001b[35m3.10.11\u001b[0m \u001b[36mrelational_config\u001b[0m=\u001b[35mcognee_db\u001b[0m \u001b[36mstructlog_version\u001b[0m=\u001b[35m25.4.0\u001b[0m \u001b[36mvector_config\u001b[0m=\u001b[35mlancedb\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:15.894641\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase storage: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "/Users/daulet/Desktop/dev/cognee-claude/.venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.3.5-local\n"
+     ]
+    }
+   ],
    "source": [
     "# Import required libraries\n",
     "import cognee\n",
+    "print(cognee.__version__)\n",
     "from cognee.shared.logging_utils import get_logger\n",
     "\n",
     "cognee.config.set_llm_model(\"gpt-4o-mini\")\n",
@@ -73,9 +98,7 @@
     "from cognee.api.v1.search import SearchType\n",
     "\n",
     "logger = get_logger()"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "markdown",
@@ -92,8 +115,10 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 3,
    "id": "4d0e4a58e4207a7d",
    "metadata": {},
+   "outputs": [],
    "source": [
     "async def run_pipeline(config=None):\n",
     "    # Clean existing data\n",
@@ -124,9 +149,7 @@
     "        )\n",
     "        answers.append(search_results)\n",
     "    return answers"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "markdown",
@@ -140,8 +163,433 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 4,
    "id": "1363772d2b48f5c0",
    "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[2m2025-10-07T20:40:24.236015\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology loaded successfully from file: ../examples/python/ontology_input_example/enriched_medical_ontology_with_classes.owl\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:24.236931\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLookup built: 4 classes, 50 individuals\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:24.348030\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mJSON extension already loaded or unavailable: Binder exception: Extension: JSON is already loaded. You can check loaded extensions by `CALL SHOW_LOADED_EXTENSIONS() RETURN *`.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:24.387417\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted Kuzu database files at /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases/cognee_graph_kuzu\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "--- Results WITH ontology ---\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[2m2025-10-07T20:40:26.930731\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase deleted successfully.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[1mStorage manager absolute path: /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_cache\u001b[0m\n",
+      "\n",
+      "\u001b[1mDeleting cache...             \u001b[0m\n",
+      "\n",
+      "\u001b[1m✓ Cache deleted successfully! \u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "User ddfe2676-fa68-430d-981e-1d335a6fdb1b has registered.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1mEmbeddingRateLimiter initialized: enabled=False, requests_limit=60, interval_seconds=60\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.202666\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `00128a51-0bd2-5512-9865-851caf7251ba`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.203107\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.203471\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.204254\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `00128a51-0bd2-5512-9865-851caf7251ba`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.204491\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.204812\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.219424\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: pypdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.219844\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: text_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.220221\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: image_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.220433\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: audio_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.220712\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: unstructured_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.220947\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRegistered loader: advanced_pdf_loader\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.LoaderEngine\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:28.221361\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mProcessing PDF: /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/nutrients-13-01241.pdf\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.advanced_pdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[1mpikepdf C++ to Python logger bridge initialized\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Warning: No languages specified, defaulting to English.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1mReading PDF for file: /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/nutrients-13-01241.pdf ...\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:35.976082\u001b[0m [\u001b[33m\u001b[1mwarning  \u001b[0m] \u001b[1mFailed to process PDF with AdvancedPdfLoader: Unable to get page count. Is poppler installed and in PATH?\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.advanced_pdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:35.977344\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mFalling back to PyPDF loader for /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/nutrients-13-01241.pdf\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.advanced_pdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:35.979542\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReading PDF: /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/nutrients-13-01241.pdf\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.pypdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.323535\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mProcessing PDF: /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/TOJ-22-0073_152Mendoza.pdf\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.advanced_pdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[1mReading PDF for file: /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/TOJ-22-0073_152Mendoza.pdf ...\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.627761\u001b[0m [\u001b[33m\u001b[1mwarning  \u001b[0m] \u001b[1mFailed to process PDF with AdvancedPdfLoader: Unable to get page count. Is poppler installed and in PATH?\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.advanced_pdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.628591\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mFalling back to PyPDF loader for /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/TOJ-22-0073_152Mendoza.pdf\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.advanced_pdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.629517\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReading PDF: /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/TOJ-22-0073_152Mendoza.pdf\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.pypdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.747011\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.747398\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.747660\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `00128a51-0bd2-5512-9865-851caf7251ba`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.750279\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.750549\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.750821\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `00128a51-0bd2-5512-9865-851caf7251ba`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.772492\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `325268f2-318a-5318-8570-3616626129ed`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.772995\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.773865\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.774764\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `325268f2-318a-5318-8570-3616626129ed`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.775056\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.775718\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.783240\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.809815\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Warning: No languages specified, defaulting to English.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.849367\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:36.863627\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.726911\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLoaded JSON extension         \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.757864\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.758561\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'michael f. mendoza' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.759088\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'ralf martz sulague' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.759456\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'therese posas-mendoza' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.759801\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'carl j. lavie' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.760065\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.760398\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee consumption' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.760701\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cardiovascular health' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.760968\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mhttp://example.org/ontology#Hypertension match was found for found for 'hypertension' node\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.763146\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mhttp://example.org/ontology#HighCholesterol match was found for found for 'cholesterol' node\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.763622\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mhttp://example.org/ontology#AtrialFibrillation match was found for found for 'atrial fibrillation' node\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.764459\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mhttp://example.org/ontology#HeartFailure match was found for found for 'heart failure' node\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.765517\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mhttp://example.org/ontology#CoronaryArteryDisease match was found for found for 'coronary heart disease' node\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.765914\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'diterpenes' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.766214\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'filtered coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.766546\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'boiled coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.766895\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'phenolic acid' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.767142\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.767407\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2023' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.767784\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'beverage' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.768084\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.768319\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health condition' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.768618\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mhttp://example.org/ontology#CardiovascularDisease match was found for found for 'cardiovascular disease' node\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.769313\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health metric' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.769628\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.769899\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chemical compound' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.770226\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'antioxidants' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.770777\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'smoking history' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.771177\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caffeine' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.771432\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'research method' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.771696\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'meta-analysis' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.771952\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cohort study' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.772202\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'behavior' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:55.772565\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mhttp://example.org/ontology#ModerateCoffeeConsumption match was found for found for 'moderate coffee consumption' node\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:40:58.393172\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.885405\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.886605\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'laura torres-collado' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.887338\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'laura maría compañ-gabucio' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.888151\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sandra gonzález-palacios' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.888781\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'leyre notario-barandiaran' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.889249\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'alejandro oncina-cánovas' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.889792\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'jesús vioque' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.890369\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'manuela garcía-de la hera' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.890717\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.891286\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee consumption' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.891705\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cardiovascular disease mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.892208\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cancer mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.892732\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'all-cause mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.893359\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mediterranean population' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.893834\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'study' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.894316\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'valencia nutrition study' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.894743\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'methodology' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.895096\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cox regression models' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.895355\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.895772\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2021-04-09' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.896129\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'nutrients 2021, 13, 1241' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.896884\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'valencia nutrition survey' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.897158\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'dietary habit' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.897435\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health condition' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.897846\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mhttp://example.org/ontology#CardiovascularDisease match was found for found for 'cardiovascular disease (cvd)' node\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.899072\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mhttp://example.org/ontology#Cancer match was found for found for 'cancer' node\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.900268\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health outcome' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.900642\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'all-cause mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.901014\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'population' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.901370\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mediterranean population' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.901726\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'research finding' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.902070\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee death association' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.902364\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee type' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.902739\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee consumption types' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.903068\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caffeinated coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.903419\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'decaffeinated coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.903728\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chemical compound' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.904073\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caffeine' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.904441\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chlorogenic acid' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.904846\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'trigonelline' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.905223\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'melanoidins' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.905559\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health benefit' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.905871\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee consumption mortality reduction' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.906210\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'beverage' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.906508\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.906740\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health behavior' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.907285\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'demographic' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.907833\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'adult population' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.908178\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'lifestyle' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.908658\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mhttp://example.org/ontology#MediterraneanDiet match was found for found for 'mediterranean lifestyle' node\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.909236\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chronic illness' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.909603\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.909852\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'research study' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.910155\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'nutritional study' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.910525\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'study participants' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.910775\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'institution' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.911136\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'ethics committee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.911403\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'data type' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:00.911738\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'data contribution' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:03.240933\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:04.242533\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:05.771183\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:05.771815\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:05.772143\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:05.772389\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:05.772610\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:05.772909\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:05.773236\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `325268f2-318a-5318-8570-3616626129ed`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:11.284104\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:15.335459\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:15.336033\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:15.336293\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:15.336526\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:15.336901\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:15.337200\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:15.337497\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `325268f2-318a-5318-8570-3616626129ed`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:15.351757\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph projection completed: 126 nodes, 264 edges in 0.00s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mCogneeGraph\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:15.656347\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mVector collection retrieval completed: Retrieved distances from 6 collections in 0.09s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:17.595983\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph projection completed: 126 nodes, 264 edges in 0.01s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mCogneeGraph\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:18.045113\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mVector collection retrieval completed: Retrieved distances from 6 collections in 0.09s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:19.425864\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph projection completed: 126 nodes, 264 edges in 0.01s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mCogneeGraph\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:19.711301\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mVector collection retrieval completed: Retrieved distances from 6 collections in 0.08s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:21.796373\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph projection completed: 126 nodes, 264 edges in 0.01s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mCogneeGraph\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:22.366335\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mVector collection retrieval completed: Retrieved distances from 6 collections in 0.09s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Q: What are common risk factors for Type 2 Diabetes?\n",
+      "A: ['Common risk factors for Type 2 Diabetes include:\\n1. Obesity\\n2. Hypertension (high blood pressure)\\n3. High cholesterol\\n4. Smoking\\n5. Cardiovascular disease\\n6. Heart failure']\n",
+      "\n",
+      "Q: What preventive measures reduce the risk of Hypertension?\n",
+      "A: ['Preventive measures to reduce the risk of hypertension include:\\n1. Low sodium diet\\n2. Moderate coffee consumption\\n3. Regular exercise\\n4. Maintaining a healthy lifestyle']\n",
+      "\n",
+      "Q: What symptoms indicate possible Cardiovascular Disease?\n",
+      "A: ['Symptoms indicating possible cardiovascular disease include:\\n1. Chest pain\\n2. Shortness of breath\\n3. Fatigue']\n",
+      "\n",
+      "Q: What diseases are associated with Obesity?\n",
+      "A: ['Diseases associated with obesity include cardiovascular disease, diabetes, hypertension, high cholesterol, and high blood pressure.']\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.134301\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLoaded JSON extension         \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
+     ]
+    }
+   ],
    "source": [
     "from cognee.modules.ontology.rdf_xml.RDFLibOntologyResolver import RDFLibOntologyResolver\n",
     "from cognee.modules.ontology.ontology_config import Config\n",
@@ -168,14 +616,411 @@
     "answers_with = await query_pipeline(questions)\n",
     "for q, a in zip(questions, answers_with):\n",
     "    print(f\"Q: {q}\\nA: {a}\\n\")"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": 5,
    "id": "3aa18f4cdd5ceff6",
    "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[2m2025-10-07T20:41:23.957345\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted Kuzu database files at /Users/daulet/Desktop/dev/cognee-claude/cognee/.cognee_system/databases/cognee_graph_kuzu\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "--- Results WITHOUT ontology ---\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[2m2025-10-07T20:41:25.980678\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase deleted successfully.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[1mDeleting cache...             \u001b[0m\n",
+      "\n",
+      "\u001b[1m✓ Cache deleted successfully! \u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:26.100988\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `d7e0340c-b6c6-568f-856c-b9f4347628d4`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:26.101412\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:26.101746\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:26.102449\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `d7e0340c-b6c6-568f-856c-b9f4347628d4`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:26.102713\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:26.103039\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:26.115879\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mProcessing PDF: /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/TOJ-22-0073_152Mendoza.pdf\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.advanced_pdf_loader\u001b[0m]\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "User 215612a9-f107-44d8-9263-d680872182c9 has registered.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1mReading PDF for file: /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/TOJ-22-0073_152Mendoza.pdf ...\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:26.605043\u001b[0m [\u001b[33m\u001b[1mwarning  \u001b[0m] \u001b[1mFailed to process PDF with AdvancedPdfLoader: Unable to get page count. Is poppler installed and in PATH?\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.advanced_pdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:26.605986\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mFalling back to PyPDF loader for /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/TOJ-22-0073_152Mendoza.pdf\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.advanced_pdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:26.606982\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReading PDF: /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/TOJ-22-0073_152Mendoza.pdf\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.pypdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:26.714728\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mProcessing PDF: /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/nutrients-13-01241.pdf\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.advanced_pdf_loader\u001b[0m]\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Warning: No languages specified, defaulting to English.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1mReading PDF for file: /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/nutrients-13-01241.pdf ...\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.139496\u001b[0m [\u001b[33m\u001b[1mwarning  \u001b[0m] \u001b[1mFailed to process PDF with AdvancedPdfLoader: Unable to get page count. Is poppler installed and in PATH?\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.advanced_pdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.140291\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mFalling back to PyPDF loader for /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/nutrients-13-01241.pdf\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.advanced_pdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.142512\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mReading PDF: /Users/daulet/Desktop/dev/cognee/examples/data/scientific_papers/nutrients-13-01241.pdf\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.infrastructure.loaders.external.pypdf_loader\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.289235\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.289621\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.289895\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `d7e0340c-b6c6-568f-856c-b9f4347628d4`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.291659\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.291909\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.292199\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `d7e0340c-b6c6-568f-856c-b9f4347628d4`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.298546\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.315361\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `8919119c-bee5-5ff1-bc01-794e8a1015ad`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.315730\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.316096\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.316653\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `8919119c-bee5-5ff1-bc01-794e8a1015ad`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.316910\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.317200\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.323905\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Warning: No languages specified, defaulting to English.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.349508\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.387202\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:27.398908\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.152674\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.153506\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'laura torres-collado' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.154051\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'laura maría compañ-gabucio' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.154641\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sandra gonzález-palacios' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.155119\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'leyre notario-barandiaran' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.155502\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'alejandro oncina-cánovas' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.155919\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'jesús vioque' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.156428\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'manuela garcía-de la hera' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.156854\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'location' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.157224\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'spain' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.157532\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'study' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.157904\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'valencia nutrition study' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.158267\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'journal' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.158702\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'nutrients' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.159018\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.159393\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2021-03-17' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.159738\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2021-04-07' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.160058\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2021-04-09' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.160442\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'beverage' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.160809\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.161047\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health condition' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.161404\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cardiovascular disease' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.161735\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cancer' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.162033\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'license' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.162473\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cc by' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.162946\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'valencia nutrition survey' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.163295\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.163722\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee consumption' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.164014\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'all cause mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.164319\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cvd mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.164705\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cancer mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.165120\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caffeinated coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.165394\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'decaffeinated coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.165657\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'statistical measure' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.165990\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffees hazard ratio' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.166280\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'medical condition' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.166547\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'oxidative stress' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.166889\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'measurement' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.167111\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person years' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.167340\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'demographic' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.167630\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.167945\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'nutrient' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.169055\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'antioxidants' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.169486\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'moderate coffee consumption' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.169838\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'population' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.170109\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'spanish population' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.170432\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'research' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.170773\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'study design' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.171027\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'self-reported data' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.171340\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chronic illness' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.171649\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'nutrition survey' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.171924\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'organization' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.172150\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'ethical committee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.172534\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health outcomes' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.172825\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee preparation method' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.173190\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'statistical power' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.173499\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'informed consent' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:48.173800\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sample size' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.669259\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.669912\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'michael f. mendoza, md' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.670464\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'ralf martz sulague, md' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.670996\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'therese posas-mendoza, md' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.671558\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'carl j. lavie, md' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.671838\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.672203\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee consumption' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.672619\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cardiovascular health' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.672998\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'hypertension' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.673312\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'heart failure' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.673566\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'atrial fibrillation' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.673909\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coronary heart disease' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.674199\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee preparation methods' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.674587\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'diterpenes' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.674834\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'phenolic acid' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.675105\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caffeine' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.675428\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.675730\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'study period 2000-2021' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.676116\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee consumption effects' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.676405\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'research type' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.676642\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'meta-analysis' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.676924\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'pilot study' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.677362\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'beverage' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.677669\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.678008\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chemicalcompound' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.678326\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'antioxidants' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.678644\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'medicalcondition' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.678986\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cardiovascular disease' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.679278\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.679582\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'behavior' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.679851\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'smoking' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.680130\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chlorogenic acid' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.680382\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'moderate coffee consumption' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.680667\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'researchstudy' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.680968\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health studies' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.681265\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'researchmethod' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.681565\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'medicalprocedure' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.681841\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cardiac surgery' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:50.725265\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:53.910668\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:57.080341\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:59.770067\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:59.803614\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:59.804032\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:59.804279\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:59.804531\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:59.804800\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:59.805061\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:41:59.805294\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `8919119c-bee5-5ff1-bc01-794e8a1015ad`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:02.709736\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:02.710292\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:02.710708\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:02.711324\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:02.711677\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:02.712008\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:02.712225\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `8919119c-bee5-5ff1-bc01-794e8a1015ad`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_with_telemetry()\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:02.725796\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph projection completed: 97 nodes, 209 edges in 0.00s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mCogneeGraph\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:03.005337\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mVector collection retrieval completed: Retrieved distances from 6 collections in 0.07s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:05.945308\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph projection completed: 97 nodes, 209 edges in 0.00s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mCogneeGraph\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:07.476846\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mVector collection retrieval completed: Retrieved distances from 6 collections in 0.08s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:11.047320\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph projection completed: 97 nodes, 209 edges in 0.01s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mCogneeGraph\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:11.394591\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mVector collection retrieval completed: Retrieved distances from 6 collections in 0.08s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:14.634449\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph projection completed: 97 nodes, 209 edges in 0.01s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mCogneeGraph\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:14.913245\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mVector collection retrieval completed: Retrieved distances from 6 collections in 0.07s\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Q: What are common risk factors for Type 2 Diabetes?\n",
+      "A: ['Common risk factors for Type 2 Diabetes include obesity (as indicated by a body mass index of 25 kg/m² or more), sedentary lifestyle, poor dietary habits, smoking habits, and the presence of chronic conditions such as hypertension and high blood cholesterol. Additionally, waist circumference measurement can indicate risk levels, with increased risk seen in men with a waist over 102 cm and women over 88 cm.']\n",
+      "\n",
+      "Q: What preventive measures reduce the risk of Hypertension?\n",
+      "A: ['Preventive measures to reduce the risk of hypertension include:\\n1. **Moderate Coffee Consumption**: Regular moderate coffee consumption (1-4 cups per day) is associated with a decreased risk of developing hypertension.\\n2. **Dietary Antioxidants**: Coffee contains antioxidants, such as chlorogenic acid, which may inhibit inflammation and support cardiovascular health.\\n3. **Healthy Preparation Methods**: Choosing filtered coffee over boiled coffee can reduce cholesterol levels and promote better heart health.\\n4. **Lifestyle Factors**: Maintaining overall cardiovascular health through lifestyle choices can also contribute to lowering the risk of hypertension.']\n",
+      "\n",
+      "Q: What symptoms indicate possible Cardiovascular Disease?\n",
+      "A: ['Possible symptoms indicating cardiovascular disease include:\\n1. Chest pain or discomfort\\n2. Shortness of breath\\n3. Fatigue or weakness\\n4. Irregular heartbeat\\n5. Swelling in the legs, ankles, or feet \\n6. Lightheadedness or dizziness \\n7. Nausea or cold sweat \\n\\nIt is important to consult a healthcare professional for proper diagnosis and treatment.']\n",
+      "\n",
+      "Q: What diseases are associated with Obesity?\n",
+      "A: ['Diseases associated with obesity include cardiovascular disease, diabetes, and hypertension. Obesity is a significant risk factor for these health conditions, often leading to increased mortality and other health complications.']\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "# Run without ontology\n",
     "print(\"\\n--- Results WITHOUT ontology ---\\n\")\n",
@@ -183,9 +1028,7 @@
     "answers_without = await query_pipeline(questions)\n",
     "for q, a in zip(questions, answers_without):\n",
     "    print(f\"Q: {q}\\nA: {a}\\n\")"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "markdown",
@@ -199,8 +1042,40 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 6,
    "id": "36ee2a360f47a054",
    "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[2m2025-10-07T20:42:22.959024\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph visualization saved as /Users/daulet/graph_visualization.html\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
+      "\n",
+      "\u001b[2m2025-10-07T20:42:22.959720\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mThe HTML file has been stored on your home directory! Navigate there with cd ~\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'/Users/daulet/graph_visualization.html'"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "import webbrowser\n",
     "import os\n",
@@ -210,9 +1085,7 @@
     "html_file = os.path.join(home_dir, \"graph_visualization.html\")\n",
     "display(html_file)\n",
     "webbrowser.open(f\"file://{html_file}\")"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "markdown",
@@ -250,8 +1123,22 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "8d2a0fe555a7bc0f",
    "metadata": {},
+   "outputs": [
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
+      "\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
+      "\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n",
+      "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
+     ]
+    }
+   ],
    "source": [
     "# Only exit in interactive mode, not during GitHub Actions\n",
     "import os\n",
@@ -262,17 +1149,15 @@
     "    os._exit(0)\n",
     "else:\n",
     "    print(\"Skipping kernel exit - running in GitHub Actions\")"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
-   "source": "",
+   "execution_count": null,
    "id": "adb6601890237b6a",
+   "metadata": {},
    "outputs": [],
-   "execution_count": null
+   "source": []
   }
  ],
  "metadata": {
@@ -291,7 +1176,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.7"
+   "version": "3.10.11"
   }
  },
  "nbformat": 4,