{ "validated_at_utc": "2026-07-12T15:30:12+00:00", "dataset_repo_id": "U4RASD/TypePrediction", "files": { "train": { "name": "type_predictor_train.jsonl", "path": "/workspace/.cache/huggingface/hub/datasets--U4RASD--TypePrediction/snapshots/2cc13badf71d134057168b7e96cf78d1fdfdc4cc/type_predictor_train.jsonl", "sha256": "20061ac6df35353e01977a85f0d6fc1466a609a093ef76a06a90f7580cbb65f8" }, "validation": { "name": "type_predictor_val.jsonl", "path": "/workspace/.cache/huggingface/hub/datasets--U4RASD--TypePrediction/snapshots/2cc13badf71d134057168b7e96cf78d1fdfdc4cc/type_predictor_val.jsonl", "sha256": "099b991973d0ba1f747c3959cbcc8a1eb98e96beadf10d7046451cfc094a19ec" }, "test": { "name": "type_predictor_test.jsonl", "path": "/workspace/.cache/huggingface/hub/datasets--U4RASD--TypePrediction/snapshots/2cc13badf71d134057168b7e96cf78d1fdfdc4cc/type_predictor_test.jsonl", "sha256": "7b494a3b7c1f3dcc14aaa9900b18dc983b4c44a8dcd02426068f32bed4f2ca0e" } }, "strict_expected_counts": true, "train": { "name": "TRAIN", "rows": 100796, "unique_ids": 100796, "type_counts": { "ORG": 21274, "PERS": 8569, "NORP": 8174, "CARDINAL": 2979, "ORDINAL": 6246, "GPE": 21521, "DATE": 15809, "OCC": 6157, "LOC": 1910, "LANGUAGE": 266, "TIME": 697, "FAC": 1037, "EVENT": 3015, "LAW": 723, "MONEY": 336, "WEBSITE": 1182, "CURR": 329, "UNIT": 85, "PERCENT": 250, "PRODUCT": 152, "QUANTITY": 85 }, "category_counts": {} }, "validation": { "name": "VALIDATION", "rows": 12600, "unique_ids": 12600, "type_counts": { "GPE": 2690, "EVENT": 377, "ORG": 2660, "DATE": 1976, "CARDINAL": 373, "OCC": 769, "ORDINAL": 780, "PERCENT": 31, "PERS": 1072, "NORP": 1022, "TIME": 87, "LOC": 239, "FAC": 130, "WEBSITE": 148, "CURR": 41, "LAW": 90, "QUANTITY": 11, "MONEY": 42, "PRODUCT": 19, "LANGUAGE": 33, "UNIT": 10 }, "category_counts": { "seen_sentence_new_entity": 11661, "unseen_sentence": 939 } }, "test": { "name": "TEST", "rows": 12600, "unique_ids": 12600, "type_counts": { "DATE": 1977, "ORG": 2659, "PERS": 1071, "NORP": 1021, "EVENT": 377, "GPE": 2691, "OCC": 770, "FAC": 129, "ORDINAL": 781, "WEBSITE": 148, "TIME": 87, "UNIT": 11, "LOC": 239, "MONEY": 42, "CARDINAL": 372, "CURR": 41, "PERCENT": 31, "LAW": 91, "PRODUCT": 19, "LANGUAGE": 33, "QUANTITY": 10 }, "category_counts": { "seen_sentence_new_entity": 11606, "unseen_sentence": 994 } }, "all_ids_unique_across_splits": true, "label_list": [ "GPE", "ORG", "DATE", "PERS", "NORP", "ORDINAL", "OCC", "EVENT", "CARDINAL", "LOC", "WEBSITE", "FAC", "LAW", "TIME", "MONEY", "CURR", "LANGUAGE", "PERCENT", "PRODUCT", "QUANTITY", "UNIT" ], "source_summary": { "total_rows": 125996, "unique_sentences": 33933, "raw_mentions_before_dedupe": 408035, "deduped_rows_before_ambiguity_filter": 132763, "duplicates_merged": 275272, "ambiguous_span_groups_excluded": 3383, "ambiguous_candidate_rows_excluded": 6767, "source_breakdown": [ { "dataset": "Wojood1_1_flat", "split": "test", "sentences": 6606, "mentions": 14573 }, { "dataset": "Wojood1_1_flat", "split": "train", "sentences": 23125, "mentions": 49959 }, { "dataset": "Wojood1_1_flat", "split": "val", "sentences": 3304, "mentions": 7143 }, { "dataset": "Wojood1_1_nested", "split": "test", "sentences": 6606, "mentions": 18045 }, { "dataset": "Wojood1_1_nested", "split": "train", "sentences": 23125, "mentions": 62377 }, { "dataset": "Wojood1_1_nested", "split": "val", "sentences": 3304, "mentions": 8944 }, { "dataset": "WojoodFine", "split": "test", "sentences": 5748, "mentions": 27848 }, { "dataset": "WojoodFine", "split": "train", "sentences": 19484, "mentions": 96188 }, { "dataset": "WojoodFine", "split": "val", "sentences": 2828, "mentions": 13800 }, { "dataset": "WojoodFine-Flat", "split": "split10", "sentences": 3304, "mentions": 10859 }, { "dataset": "WojoodFine-Flat", "split": "split20", "sentences": 6606, "mentions": 22208 }, { "dataset": "WojoodFine-Flat", "split": "split70", "sentences": 23125, "mentions": 76091 } ], "type_breakdown": [ { "type": "GPE", "count": 26902 }, { "type": "ORG", "count": 26593 }, { "type": "DATE", "count": 19762 }, { "type": "PERS", "count": 10712 }, { "type": "NORP", "count": 10217 }, { "type": "ORDINAL", "count": 7807 }, { "type": "OCC", "count": 7696 }, { "type": "EVENT", "count": 3769 }, { "type": "CARDINAL", "count": 3724 }, { "type": "LOC", "count": 2388 }, { "type": "WEBSITE", "count": 1478 }, { "type": "FAC", "count": 1296 }, { "type": "LAW", "count": 904 }, { "type": "TIME", "count": 871 }, { "type": "MONEY", "count": 420 }, { "type": "CURR", "count": 411 }, { "type": "LANGUAGE", "count": 332 }, { "type": "PERCENT", "count": 312 }, { "type": "PRODUCT", "count": 190 }, { "type": "QUANTITY", "count": 106 }, { "type": "UNIT", "count": 106 } ] }, "source_split_summary": { "random_seed": 42, "requested_split_ratios": { "train": 0.8, "validation": 0.1, "test": 0.1 }, "totals": { "original_rows": 125996, "train_rows": 100796, "validation_rows": 12600, "test_rows": 12600 }, "splits": { "train": { "name": "train", "rows": 100796, "percentage": 0.7999936505920823, "unique_sentences": 32409, "type_counts": { "CARDINAL": 2979, "CURR": 329, "DATE": 15809, "EVENT": 3015, "FAC": 1037, "GPE": 21521, "LANGUAGE": 266, "LAW": 723, "LOC": 1910, "MONEY": 336, "NORP": 8174, "OCC": 6157, "ORDINAL": 6246, "ORG": 21274, "PERCENT": 250, "PERS": 8569, "PRODUCT": 152, "QUANTITY": 85, "TIME": 697, "UNIT": 85, "WEBSITE": 1182 } }, "validation": { "name": "validation", "rows": 12600, "percentage": 0.10000317470395885, "unique_sentences": 10139, "type_counts": { "CARDINAL": 373, "CURR": 41, "DATE": 1976, "EVENT": 377, "FAC": 130, "GPE": 2690, "LANGUAGE": 33, "LAW": 90, "LOC": 239, "MONEY": 42, "NORP": 1022, "OCC": 769, "ORDINAL": 780, "ORG": 2660, "PERCENT": 31, "PERS": 1072, "PRODUCT": 19, "QUANTITY": 11, "TIME": 87, "UNIT": 10, "WEBSITE": 148 } }, "test": { "name": "test", "rows": 12600, "percentage": 0.10000317470395885, "unique_sentences": 10161, "type_counts": { "CARDINAL": 372, "CURR": 41, "DATE": 1977, "EVENT": 377, "FAC": 129, "GPE": 2691, "LANGUAGE": 33, "LAW": 91, "LOC": 239, "MONEY": 42, "NORP": 1021, "OCC": 770, "ORDINAL": 781, "ORG": 2659, "PERCENT": 31, "PERS": 1071, "PRODUCT": 19, "QUANTITY": 10, "TIME": 87, "UNIT": 11, "WEBSITE": 148 } } }, "per_type_counts": { "CARDINAL": { "original": 3724, "train": 2979, "validation": 373, "test": 372, "train_ratio": 0.7999462943071965, "validation_ratio": 0.10016111707841031, "test_ratio": 0.09989258861439312 }, "CURR": { "original": 411, "train": 329, "validation": 41, "test": 41, "train_ratio": 0.8004866180048662, "validation_ratio": 0.09975669099756691, "test_ratio": 0.09975669099756691 }, "DATE": { "original": 19762, "train": 15809, "validation": 1976, "test": 1977, "train_ratio": 0.7999696387005364, "validation_ratio": 0.09998987956684546, "test_ratio": 0.10004048173261816 }, "EVENT": { "original": 3769, "train": 3015, "validation": 377, "test": 377, "train_ratio": 0.7999469355266648, "validation_ratio": 0.10002653223666755, "test_ratio": 0.10002653223666755 }, "FAC": { "original": 1296, "train": 1037, "validation": 130, "test": 129, "train_ratio": 0.8001543209876543, "validation_ratio": 0.10030864197530864, "test_ratio": 0.09953703703703703 }, "GPE": { "original": 26902, "train": 21521, "validation": 2690, "test": 2691, "train_ratio": 0.7999776968255148, "validation_ratio": 0.09999256560850495, "test_ratio": 0.10002973756598023 }, "LANGUAGE": { "original": 332, "train": 266, "validation": 33, "test": 33, "train_ratio": 0.8012048192771084, "validation_ratio": 0.09939759036144578, "test_ratio": 0.09939759036144578 }, "LAW": { "original": 904, "train": 723, "validation": 90, "test": 91, "train_ratio": 0.7997787610619469, "validation_ratio": 0.09955752212389381, "test_ratio": 0.1006637168141593 }, "LOC": { "original": 2388, "train": 1910, "validation": 239, "test": 239, "train_ratio": 0.7998324958123953, "validation_ratio": 0.10008375209380234, "test_ratio": 0.10008375209380234 }, "MONEY": { "original": 420, "train": 336, "validation": 42, "test": 42, "train_ratio": 0.8, "validation_ratio": 0.1, "test_ratio": 0.1 }, "NORP": { "original": 10217, "train": 8174, "validation": 1022, "test": 1021, "train_ratio": 0.8000391504355486, "validation_ratio": 0.10002936282666144, "test_ratio": 0.09993148673778995 }, "OCC": { "original": 7696, "train": 6157, "validation": 769, "test": 770, "train_ratio": 0.8000259875259875, "validation_ratio": 0.09992203742203742, "test_ratio": 0.10005197505197505 }, "ORDINAL": { "original": 7807, "train": 6246, "validation": 780, "test": 781, "train_ratio": 0.8000512360701935, "validation_ratio": 0.09991033687716153, "test_ratio": 0.10003842705264507 }, "ORG": { "original": 26593, "train": 21274, "validation": 2660, "test": 2659, "train_ratio": 0.7999849584477118, "validation_ratio": 0.10002632271650434, "test_ratio": 0.09998871883578385 }, "PERCENT": { "original": 312, "train": 250, "validation": 31, "test": 31, "train_ratio": 0.8012820512820513, "validation_ratio": 0.09935897435897435, "test_ratio": 0.09935897435897435 }, "PERS": { "original": 10712, "train": 8569, "validation": 1072, "test": 1071, "train_ratio": 0.7999439880507841, "validation_ratio": 0.10007468259895444, "test_ratio": 0.09998132935026138 }, "PRODUCT": { "original": 190, "train": 152, "validation": 19, "test": 19, "train_ratio": 0.8, "validation_ratio": 0.1, "test_ratio": 0.1 }, "QUANTITY": { "original": 106, "train": 85, "validation": 11, "test": 10, "train_ratio": 0.8018867924528302, "validation_ratio": 0.10377358490566038, "test_ratio": 0.09433962264150944 }, "TIME": { "original": 871, "train": 697, "validation": 87, "test": 87, "train_ratio": 0.8002296211251435, "validation_ratio": 0.09988518943742825, "test_ratio": 0.09988518943742825 }, "UNIT": { "original": 106, "train": 85, "validation": 10, "test": 11, "train_ratio": 0.8018867924528302, "validation_ratio": 0.09433962264150944, "test_ratio": 0.10377358490566038 }, "WEBSITE": { "original": 1478, "train": 1182, "validation": 148, "test": 148, "train_ratio": 0.7997293640054127, "validation_ratio": 0.10013531799729364, "test_ratio": 0.10013531799729364 } }, "evaluation_category_counts": { "validation": { "seen_sentence_new_entity": 11661, "unseen_sentence": 939 }, "test": { "seen_sentence_new_entity": 11606, "unseen_sentence": 994 } }, "evaluation_category_counts_by_type": { "validation": { "CARDINAL": { "unseen_sentence": 49, "seen_sentence_new_entity": 324 }, "CURR": { "unseen_sentence": 2, "seen_sentence_new_entity": 39 }, "DATE": { "unseen_sentence": 124, "seen_sentence_new_entity": 1852 }, "EVENT": { "unseen_sentence": 15, "seen_sentence_new_entity": 362 }, "FAC": { "unseen_sentence": 13, "seen_sentence_new_entity": 117 }, "GPE": { "unseen_sentence": 159, "seen_sentence_new_entity": 2531 }, "LANGUAGE": { "unseen_sentence": 3, "seen_sentence_new_entity": 30 }, "LAW": { "unseen_sentence": 7, "seen_sentence_new_entity": 83 }, "LOC": { "unseen_sentence": 17, "seen_sentence_new_entity": 222 }, "MONEY": { "unseen_sentence": 1, "seen_sentence_new_entity": 41 }, "NORP": { "unseen_sentence": 101, "seen_sentence_new_entity": 921 }, "OCC": { "unseen_sentence": 45, "seen_sentence_new_entity": 724 }, "ORDINAL": { "unseen_sentence": 89, "seen_sentence_new_entity": 691 }, "ORG": { "unseen_sentence": 114, "seen_sentence_new_entity": 2546 }, "PERCENT": { "unseen_sentence": 2, "seen_sentence_new_entity": 29 }, "PERS": { "unseen_sentence": 145, "seen_sentence_new_entity": 927 }, "PRODUCT": { "unseen_sentence": 3, "seen_sentence_new_entity": 16 }, "QUANTITY": { "unseen_sentence": 0, "seen_sentence_new_entity": 11 }, "TIME": { "unseen_sentence": 12, "seen_sentence_new_entity": 75 }, "UNIT": { "unseen_sentence": 1, "seen_sentence_new_entity": 9 }, "WEBSITE": { "unseen_sentence": 37, "seen_sentence_new_entity": 111 } }, "test": { "CARDINAL": { "unseen_sentence": 49, "seen_sentence_new_entity": 323 }, "CURR": { "unseen_sentence": 3, "seen_sentence_new_entity": 38 }, "DATE": { "unseen_sentence": 120, "seen_sentence_new_entity": 1857 }, "EVENT": { "unseen_sentence": 14, "seen_sentence_new_entity": 363 }, "FAC": { "unseen_sentence": 8, "seen_sentence_new_entity": 121 }, "GPE": { "unseen_sentence": 153, "seen_sentence_new_entity": 2538 }, "LANGUAGE": { "unseen_sentence": 8, "seen_sentence_new_entity": 25 }, "LAW": { "unseen_sentence": 8, "seen_sentence_new_entity": 83 }, "LOC": { "unseen_sentence": 15, "seen_sentence_new_entity": 224 }, "MONEY": { "unseen_sentence": 1, "seen_sentence_new_entity": 41 }, "NORP": { "unseen_sentence": 125, "seen_sentence_new_entity": 896 }, "OCC": { "unseen_sentence": 50, "seen_sentence_new_entity": 720 }, "ORDINAL": { "unseen_sentence": 82, "seen_sentence_new_entity": 699 }, "ORG": { "unseen_sentence": 139, "seen_sentence_new_entity": 2520 }, "PERCENT": { "unseen_sentence": 2, "seen_sentence_new_entity": 29 }, "PERS": { "unseen_sentence": 143, "seen_sentence_new_entity": 928 }, "PRODUCT": { "unseen_sentence": 2, "seen_sentence_new_entity": 17 }, "QUANTITY": { "unseen_sentence": 1, "seen_sentence_new_entity": 9 }, "TIME": { "unseen_sentence": 19, "seen_sentence_new_entity": 68 }, "UNIT": { "unseen_sentence": 0, "seen_sentence_new_entity": 11 }, "WEBSITE": { "unseen_sentence": 52, "seen_sentence_new_entity": 96 } } }, "validation": { "ok": true, "errors": [] } } }