{"_id": {"$oid": "69d4eb12b877594bc5718a68"}, "test_id": "T0443", "benchmark": "company_lists", "date": "2025-11-25", "tags": {"document-type": ["book-page"], "writing": ["printed"], "century": [20], "language": ["en", "de"], "layout": ["list"], "entry-type": ["company"], "task": ["information-extraction"]}, "contributors": ["lea_kasper", "sorin_marti"], "hidden": false, "config": {"provider": "mistral", "model": "mistral-small-2506", "dataclass": "ListPage", "temperature": 0.5, "role_description": "You are a Historian", "prompt_file": "prompt.txt", "legacy_test": false}, "prompt": "The image you are presented with stems from a digitized book containing lists of companies.\nYour task is to extract structured information about each company listed on the page.\n\nAbout the source:\n- The image stems from a trade index of the British Swiss Chamber of Commerce.\n- The image can show an alphabetical or a thematic list of companies.\n- The companies are mostly located in Switzerland and the UK.\n- The image stems from a trade index between 1925 and 1958.\n- Most pages have one column but some years have two columns.\n- The source itself is in English and German but the company names can be in English, German, French or Italian.\n\nAbout the entries:\n- Each entry describes a single company or person.\n- Alphabetical entries have filling dots between the company name and the page number. Dots and page numbers are not part of the data and should be ignored.\n- Alphabetical entries seldom to never have locations.\n- Thematic entries often have locations.\n- Thematic entries are listed under headings that describe the type of business.\n- Some thematic headings are only references to other headings, e.g. \"X, s. Y\".\n\nAbout the output:\n- Answer in valid JSON. The JSON should be an array of objects with the following fields:\n- The page ID is given as {page_id}.\n- Do not add country information, if it is not directly written with the location.\n\n{\n  \"entry_id\": \"A unique identifier for the entry, e.g. '{page_id}-1'\",\n  \"company_name\": \"The name of the company or person\",\n  \"location\": \"The location of the company, e.g. 'Zurich' or 'London, UK'. If no location is given, set to null.\"\n  ]\n}\n", "results": {"text": "{\n  \"page_id\": \"{page_id}\",\n  \"entries\": [\n    {\n      \"entry_id\": \"{page_id}-1\",\n      \"company_name\": \"Example Company\",\n      \"location\": null\n    },\n    {\n      \"entry_id\": \"{page_id}-2\",\n      \"company_name\": \"Another Company\",\n      \"location\": \"Zurich\"\n    }\n  ]\n}", "model": "mistral-small-2506", "provider": "mistral", "finish_reason": "stop", "usage": {"input_tokens": 548, "output_tokens": 81, "total_tokens": 629, "input_cost_usd": 5.4800000000000004e-05, "output_cost_usd": 2.43e-05, "estimated_cost_usd": 7.91e-05}, "duration": 0.9701170921325684, "timestamp": "2025-11-25T11:40:05.704305", "score": {"f1_score": 0.0, "precision": 0.0, "recall": 0.0, "true_positives": 0, "false_positives": 0, "false_negatives": 52, "field_scores": {"": {"response": "", "ground_truth": "", "score": 1.0}, "entries[16].location": {"response": "", "ground_truth": "Geneva", "score": 0.0}, "entries[5].entry_id": {"response": "", "ground_truth": "156089_1321093_11-6", "score": 0.0}, "entries[4].entry_id": {"response": "", "ground_truth": "156089_1321093_11-5", "score": 0.0}, "entries[13].location": {"response": "", "ground_truth": "Geneva", "score": 0.0}, "entries[8].company_name": {"response": "", "ground_truth": "J. Hopf & Co. (Merchants)", "score": 0.0}, "entries[15].location": {"response": "", "ground_truth": "Lausanne", "score": 0.0}, "entries[6].company_name": {"response": "", "ground_truth": "J. R. Geigy, A.-G.", "score": 0.0}, "entries[11].entry_id": {"response": "", "ground_truth": "156089_1321093_11-12", "score": 0.0}, "entries[10].company_name": {"response": "", "ground_truth": "Banque F\u00e9d\u00e9rale S.A.", "score": 0.0}, "entries[16].company_name": {"response": "", "ground_truth": "Wagons-Lits/Cook S.A.", "score": 0.0}, "entries[2].company_name": {"response": "", "ground_truth": "Metallwerke A.G.", "score": 0.0}, "entries[6].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[9].company_name": {"response": "", "ground_truth": "Rayon A.-G. (Merchants)", "score": 0.0}, "entries[3].company_name": {"response": "", "ground_truth": "Aluminium-Industrie-Aktien-Gesellschaft", "score": 0.0}, "entries[1].company_name": {"response": "", "ground_truth": "Imperial Airways Ltd.", "score": 0.0}, "entries[0].company_name": {"response": "", "ground_truth": "Crowe & Co., Ltd.", "score": 0.0}, "entries[11].company_name": {"response": "", "ground_truth": "Barclays Bank Ltd. (Foreign Branch)", "score": 0.0}, "entries[14].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[2].entry_id": {"response": "", "ground_truth": "156089_1321093_11-3", "score": 0.0}, "page_id": {"response": "", "ground_truth": "156089_1321093_11", "score": 0.0}, "entries[12].entry_id": {"response": "", "ground_truth": "156089_1321093_11-13", "score": 0.0}, "entries[1].entry_id": {"response": "", "ground_truth": "156089_1321093_11-2", "score": 0.0}, "entries[0].entry_id": {"response": "", "ground_truth": "156089_1321093_11-1", "score": 0.0}, "entries[14].entry_id": {"response": "", "ground_truth": "156089_1321093_11-15", "score": 0.0}, "entries[3].entry_id": {"response": "", "ground_truth": "156089_1321093_11-4", "score": 0.0}, "entries[15].company_name": {"response": "", "ground_truth": "Swiss Bank Corporation", "score": 0.0}, "entries[15].entry_id": {"response": "", "ground_truth": "156089_1321093_11-16", "score": 0.0}, "entries[8].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[0].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[9].entry_id": {"response": "", "ground_truth": "156089_1321093_11-10", "score": 0.0}, "entries[7].company_name": {"response": "", "ground_truth": "Society of Chemical Industry in Basle", "score": 0.0}, "entries[10].entry_id": {"response": "", "ground_truth": "156089_1321093_11-11", "score": 0.0}, "entries[1].location": {"response": "", "ground_truth": "Croydon", "score": 0.0}, "entries[4].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[5].company_name": {"response": "", "ground_truth": "Clayton Aniline Co., Ltd.", "score": 0.0}, "entries[9].location": {"response": "", "ground_truth": "Arlesheim", "score": 0.0}, "entries[11].location": {"response": "", "ground_truth": "London E.C. 3.", "score": 0.0}, "entries[4].company_name": {"response": "", "ground_truth": "Chemische Fabrik vorm. Sandoz", "score": 0.0}, "entries[13].company_name": {"response": "", "ground_truth": "Lloyds and National Provincial Foreign Bank, Ltd.", "score": 0.0}, "entries[14].company_name": {"response": "", "ground_truth": "Swiss Bank Corporation", "score": 0.0}, "entries[12].company_name": {"response": "", "ground_truth": "Galland & Co.", "score": 0.0}, "entries[12].location": {"response": "", "ground_truth": "Lausanne", "score": 0.0}, "entries[13].entry_id": {"response": "", "ground_truth": "156089_1321093_11-14", "score": 0.0}, "entries[7].entry_id": {"response": "", "ground_truth": "156089_1321093_11-8", "score": 0.0}, "entries[6].entry_id": {"response": "", "ground_truth": "156089_1321093_11-7", "score": 0.0}, "entries[8].entry_id": {"response": "", "ground_truth": "156089_1321093_11-9", "score": 0.0}, "entries[10].location": {"response": "", "ground_truth": "Vevey", "score": 0.0}, "entries[5].location": {"response": "", "ground_truth": "Manchester", "score": 0.0}, "entries[7].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[3].location": {"response": "", "ground_truth": "Neuhausen", "score": 0.0}, "entries[2].location": {"response": "", "ground_truth": "Dornach (Solothurn)", "score": 0.0}, "entries[16].entry_id": {"response": "", "ground_truth": "156089_1321093_11-17", "score": 0.0}}, "total_fields": 53}, "raw_response": "{\"id\":\"9d5a4a3ba4fc487a988f95de660587e0\",\"object\":\"chat.completion\",\"model\":\"mistral-small-2506\",\"usage\":{\"prompt_tokens\":548,\"completion_tokens\":81,\"total_tokens\":629},\"created\":1764067204,\"choices\":[{\"index\":0,\"message\":{\"content\":\"{\\n  \\\"page_id\\\": \\\"{page_id}\\\",\\n  \\\"entries\\\": [\\n    {\\n      \\\"entry_id\\\": \\\"{page_id}-1\\\",\\n      \\\"company_name\\\": \\\"Example Company\\\",\\n      \\\"location\\\": null\\n    },\\n    {\\n      \\\"entry_id\\\": \\\"{page_id}-2\\\",\\n      \\\"company_name\\\": \\\"Another Company\\\",\\n      \\\"location\\\": \\\"Zurich\\\"\\n    }\\n  ]\\n}\",\"tool_calls\":null,\"prefix\":false,\"role\":\"assistant\"},\"finish_reason\":\"stop\"}]}"}, "scoring": {"f1_micro": 0.001988071570576541, "f1_macro": 0.0006666666666666666, "micro_precision": 0.07142857142857142, "micro_recall": 0.0010080645161290322, "total_instances": 15, "total_tp": 1, "total_fp": 13, "total_fn": 991, "cost_summary": {"total_input_tokens": 8220, "total_output_tokens": 1388, "total_tokens": 9608, "input_cost_usd": 0.0008220000000000004, "output_cost_usd": 0.00041639999999999993, "total_cost_usd": 0.0012384000000000002}}, "normalized_score": 0.06666666666666667}