{"_id": {"$oid": "69d4eb12b877594bc5718be8"}, "test_id": "T0551", "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": "ministral-14b-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\":\"{page_id}\",\"entries\":[]}", "model": "ministral-14b-2512", "provider": "mistral", "finish_reason": "stop", "usage": {"input_tokens": 548, "output_tokens": 17, "total_tokens": 565, "input_cost_usd": 0.00010960000000000001, "output_cost_usd": 3.4e-06, "estimated_cost_usd": 0.00011300000000000001}, "duration": 0.3058030605316162, "timestamp": "2026-01-25T00:40:22.850401", "parsed": {"page_id": "{page_id}", "entries": []}, "conversation_id": "cfe5d68a-eb80-4216-bb24-4145c3845801", "score": {"f1_score": 0.0, "precision": 0.0, "recall": 0.0, "true_positives": 0, "false_positives": 1, "false_negatives": 52, "field_scores": {"entries[0].entry_id": {"response": "", "ground_truth": "156089_1321081_14-1", "score": 0.0}, "entries[15].company_name": {"response": "", "ground_truth": "Schw. Seidengazefabrik A. G.", "score": 0.0}, "entries[9].entry_id": {"response": "", "ground_truth": "156089_1321081_14-10", "score": 0.0}, "entries[9].location": {"response": "", "ground_truth": "Flawil", "score": 0.0}, "entries[9].company_name": {"response": "", "ground_truth": "Altherr & Guex", "score": 0.0}, "entries[5].company_name": {"response": "", "ground_truth": "Louis Kohler", "score": 0.0}, "entries[3].location": {"response": "", "ground_truth": "Maidstone, Kent", "score": 0.0}, "entries[3].company_name": {"response": "", "ground_truth": "Barcham Green & Sons", "score": 0.0}, "entries[7].entry_id": {"response": "", "ground_truth": "156089_1321081_14-8", "score": 0.0}, "entries[13].location": {"response": "", "ground_truth": "Zurzach", "score": 0.0}, "entries[0].company_name": {"response": "", "ground_truth": "Swiss Bank Corporation", "score": 0.0}, "entries[16].location": {"response": "", "ground_truth": "Z\u00fcrich", "score": 0.0}, "entries[8].company_name": {"response": "", "ground_truth": "August Fr\u00f6hlich", "score": 0.0}, "entries[12].location": {"response": "", "ground_truth": "Nottingham", "score": 0.0}, "entries[10].location": {"response": "", "ground_truth": "Arbon", "score": 0.0}, "entries[10].entry_id": {"response": "", "ground_truth": "156089_1321081_14-11", "score": 0.0}, "entries[8].location": {"response": "", "ground_truth": "Z\u00fcrich", "score": 0.0}, "entries[6].entry_id": {"response": "", "ground_truth": "156089_1321081_14-7", "score": 0.0}, "entries[14].entry_id": {"response": "", "ground_truth": "156089_1321081_14-15", "score": 0.0}, "entries[4].location": {"response": "", "ground_truth": "Gen\u00e8ve", "score": 0.0}, "entries[5].location": {"response": "", "ground_truth": "Lausanne", "score": 0.0}, "entries[15].location": {"response": "", "ground_truth": "Thal, bei Rheineck", "score": 0.0}, "entries[10].company_name": {"response": "", "ground_truth": "Arbon Embroidery Works Ltd.", "score": 0.0}, "entries[11].company_name": {"response": "", "ground_truth": "Grieder & Co.", "score": 0.0}, "entries[13].company_name": {"response": "", "ground_truth": "Zuberb\u00fchler & Co., A. G.", "score": 0.0}, "entries[13].entry_id": {"response": "", "ground_truth": "156089_1321081_14-14", "score": 0.0}, "page_id": {"response": "{page_id}", "ground_truth": "156089_1321081_14", "score": 0.07692307692307687}, "entries[1].company_name": {"response": "", "ground_truth": "Swiss Bank Corporation", "score": 0.0}, "entries[4].company_name": {"response": "", "ground_truth": "Herren & Guerchet", "score": 0.0}, "entries[16].company_name": {"response": "", "ground_truth": "Schw. Seidengazefabrik A. G.", "score": 0.0}, "entries[1].location": {"response": "", "ground_truth": "Neuch\u00e2tel", "score": 0.0}, "entries[7].company_name": {"response": "", "ground_truth": "Georges Michoud", "score": 0.0}, "entries[11].location": {"response": "", "ground_truth": "Z\u00fcrich", "score": 0.0}, "entries[8].entry_id": {"response": "", "ground_truth": "156089_1321081_14-9", "score": 0.0}, "entries[4].entry_id": {"response": "", "ground_truth": "156089_1321081_14-5", "score": 0.0}, "entries[7].location": {"response": "", "ground_truth": "Lausanne", "score": 0.0}, "entries[0].location": {"response": "", "ground_truth": "Lausanne", "score": 0.0}, "entries[6].company_name": {"response": "", "ground_truth": "Giuliniwerke A. G.", "score": 0.0}, "entries[2].entry_id": {"response": "", "ground_truth": "156089_1321081_14-3", "score": 0.0}, "entries[12].company_name": {"response": "", "ground_truth": "A. C. Pearse Ltd.", "score": 0.0}, "entries[2].location": {"response": "", "ground_truth": "Z\u00fcrich", "score": 0.0}, "entries[5].entry_id": {"response": "", "ground_truth": "156089_1321081_14-6", "score": 0.0}, "entries[11].entry_id": {"response": "", "ground_truth": "156089_1321081_14-12", "score": 0.0}, "entries[2].company_name": {"response": "", "ground_truth": "Union Bank of Switzerland", "score": 0.0}, "entries[12].entry_id": {"response": "", "ground_truth": "156089_1321081_14-13", "score": 0.0}, "entries[3].entry_id": {"response": "", "ground_truth": "156089_1321081_14-4", "score": 0.0}, "entries[1].entry_id": {"response": "", "ground_truth": "156089_1321081_14-2", "score": 0.0}, "entries[14].company_name": {"response": "", "ground_truth": "Sulzer Fr\u00e8res S. A.", "score": 0.0}, "entries[15].entry_id": {"response": "", "ground_truth": "156089_1321081_14-16", "score": 0.0}, "entries[16].entry_id": {"response": "", "ground_truth": "156089_1321081_14-17", "score": 0.0}, "entries[14].location": {"response": "", "ground_truth": "Winterthur", "score": 0.0}, "entries[6].location": {"response": "", "ground_truth": "Basel", "score": 0.0}}, "total_fields": 52}, "raw_response": "{\"id\":\"7f69a430357848709160172401a68430\",\"object\":\"chat.completion\",\"model\":\"ministral-14b-2512\",\"usage\":{\"prompt_tokens\":548,\"completion_tokens\":17,\"total_tokens\":565,\"num_cached_tokens\":512},\"created\":1769298022,\"choices\":[{\"index\":0,\"message\":{\"content\":\"{\\n  \\\"page_id\\\": \\\"{page_id}\\\",\\n  \\\"entries\\\": []\\n}\",\"tool_calls\":null,\"prefix\":false,\"role\":\"assistant\"},\"finish_reason\":\"stop\"}]}"}, "scoring": {"f1_micro": 0.0, "f1_macro": 0.0, "micro_precision": 0.0, "micro_recall": 0.0, "total_instances": 15, "total_tp": 0, "total_fp": 15, "total_fn": 992, "cost_summary": {"total_input_tokens": 8220, "total_output_tokens": 255, "total_tokens": 8475, "input_cost_usd": 0.0016440000000000007, "output_cost_usd": 5.100000000000001e-05, "total_cost_usd": 0.0016950000000000003}}, "normalized_score": 0}