{"_id": {"$oid": "6a26c67c3572c06bc1455bc3"}, "test_id": "T0540", "benchmark": "company_lists", "date": "2026-01-25", "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-large-2512", "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": "{\"page_id\":\"unknown\",\"entries\":[]}", "model": "mistral-large-2512", "provider": "mistral", "finish_reason": "stop", "usage": {"input_tokens": 548, "output_tokens": 13, "total_tokens": 561, "input_cost_usd": 0.000274, "output_cost_usd": 1.95e-05, "estimated_cost_usd": 0.0002935}, "duration": 0.7289321422576904, "timestamp": "2026-01-25T00:01:52.633012", "parsed": {"page_id": "unknown", "entries": []}, "conversation_id": "eb050b1f-a55f-4abd-81e7-148e5d8e00a7", "score": {"f1_score": 0.0, "precision": 0.0, "recall": 0.0, "true_positives": 0, "false_positives": 1, "false_negatives": 37, "field_scores": {"entries[0].entry_id": {"response": "", "ground_truth": "156089_1321092_18-1", "score": 0.0}, "entries[9].entry_id": {"response": "", "ground_truth": "156089_1321092_18-10", "score": 0.0}, "entries[9].location": {"response": "", "ground_truth": "Baden (Switzerland)", "score": 0.0}, "entries[9].company_name": {"response": "", "ground_truth": "Brown Boveri & Cie., A.-G.", "score": 0.0}, "entries[5].company_name": {"response": "", "ground_truth": "Magn\u00e9tos Lucifer S. A.", "score": 0.0}, "entries[3].location": {"response": "", "ground_truth": "Baden (Switzerland)", "score": 0.0}, "entries[3].company_name": {"response": "", "ground_truth": "Brown Boveri & Cie., A.-G.", "score": 0.0}, "entries[7].entry_id": {"response": "", "ground_truth": "156089_1321092_18-8", "score": 0.0}, "entries[0].company_name": {"response": "", "ground_truth": "F\u00e4rbereien Schetty, A.-G.", "score": 0.0}, "entries[8].company_name": {"response": "", "ground_truth": "Brown Boveri & Cie., A.-G.", "score": 0.0}, "entries[10].location": {"response": "", "ground_truth": "Baden (Switzerland)", "score": 0.0}, "entries[10].entry_id": {"response": "", "ground_truth": "156089_1321092_18-11", "score": 0.0}, "entries[8].location": {"response": "", "ground_truth": "Baden (Switzerland)", "score": 0.0}, "entries[6].entry_id": {"response": "", "ground_truth": "156089_1321092_18-7", "score": 0.0}, "entries[4].location": {"response": "", "ground_truth": "Baden (Switzerland)", "score": 0.0}, "entries[5].location": {"response": "", "ground_truth": "Carouge-Gen\u00e8ve", "score": 0.0}, "entries[10].company_name": {"response": "", "ground_truth": "Brown Boveri & Cie., A.-G.", "score": 0.0}, "entries[11].company_name": {"response": "", "ground_truth": "Brown Boveri & Cie., A.-G.", "score": 0.0}, "page_id": {"response": "unknown", "ground_truth": "156089_1321092_18", "score": 0.0}, "entries[1].company_name": {"response": "", "ground_truth": "G. Kappeler A.-G.", "score": 0.0}, "entries[4].company_name": {"response": "", "ground_truth": "Brown Boveri & Cie., A.-G.", "score": 0.0}, "entries[1].location": {"response": "", "ground_truth": "Zofingen", "score": 0.0}, "entries[7].company_name": {"response": "", "ground_truth": "Brown Boveri & Cie., A.-G.", "score": 0.0}, "entries[11].location": {"response": "", "ground_truth": "Baden (Switzerland)", "score": 0.0}, "entries[8].entry_id": {"response": "", "ground_truth": "156089_1321092_18-9", "score": 0.0}, "entries[4].entry_id": {"response": "", "ground_truth": "156089_1321092_18-5", "score": 0.0}, "entries[7].location": {"response": "", "ground_truth": "Baden (Switzerland)", "score": 0.0}, "entries[0].location": {"response": "", "ground_truth": "Basle", "score": 0.0}, "entries[6].company_name": {"response": "", "ground_truth": "Brown Boveri & Cie., A.-G.", "score": 0.0}, "entries[2].entry_id": {"response": "", "ground_truth": "156089_1321092_18-3", "score": 0.0}, "entries[2].location": {"response": "", "ground_truth": "Walsall, England", "score": 0.0}, "entries[5].entry_id": {"response": "", "ground_truth": "156089_1321092_18-6", "score": 0.0}, "entries[11].entry_id": {"response": "", "ground_truth": "156089_1321092_18-12", "score": 0.0}, "entries[2].company_name": {"response": "", "ground_truth": "J. A. Crabtree & Co., Ltd.", "score": 0.0}, "entries[3].entry_id": {"response": "", "ground_truth": "156089_1321092_18-4", "score": 0.0}, "entries[1].entry_id": {"response": "", "ground_truth": "156089_1321092_18-2", "score": 0.0}, "entries[6].location": {"response": "", "ground_truth": "Baden (Switzerland)", "score": 0.0}}, "total_fields": 37}, "raw_response": "{\"id\":\"d5c892acd7b14fc1ad74fc5c8aa43c9d\",\"object\":\"chat.completion\",\"model\":\"mistral-large-2512\",\"usage\":{\"prompt_tokens\":548,\"completion_tokens\":13,\"total_tokens\":561,\"num_cached_tokens\":575},\"created\":1769295712,\"choices\":[{\"index\":0,\"message\":{\"content\":\"{\\\"page_id\\\": \\\"unknown\\\", \\\"entries\\\": []}\",\"tool_calls\":null,\"prefix\":false,\"role\":\"assistant\"},\"finish_reason\":\"stop\"}]}"}, "scoring": {"f1_micro": 0.003110419906687403, "f1_macro": 0.0026666666666666666, "micro_precision": 0.006802721088435374, "micro_recall": 0.0020161290322580645, "total_instances": 15, "total_tp": 2, "total_fp": 292, "total_fn": 990, "cost_summary": {"total_input_tokens": 8220, "total_output_tokens": 10004, "total_tokens": 18224, "input_cost_usd": 0.00411, "output_cost_usd": 0.015006, "total_cost_usd": 0.019115999999999998}}, "normalized_score": 0.26666666666666666}