{"adoption": {"forks": 245, "observed_at": "2026-08-28T04:05:05.772324+00:00", "stars": 1574}, "canonical_url": "https://ross.abutalabs.com/products/entity-recognition-datasets", "card": {"archived": false, "artifact_type": "dataset", "description": "A collection of corpora for named entity recognition (NER) and entity recognition tasks. These annotated datasets cover a variety of languages, domains and entity types.", "domain": ["machine-learning", "data-science"], "enriched": true, "function": ["nlp", "data-science"], "health_score": 74, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["juand-r/entity-recognition-datasets"], "name": "juand-r/entity-recognition-datasets", "platform": ["python", "cross-platform"], "pushed_at": "2026-07-02T04:27:10+00:00", "repo": "juand-r/entity-recognition-datasets", "stars": 1574, "tags": ["named-entity-recognition", "ner", "corpora", "entity-extraction", "conll-format", "dataset-collection", "natural-language-processing"], "topics": ["entity-extraction", "named-entity-recognition", "ner", "datasets", "entity-recognition", "nlp-resources", "nlp", "corpora", "natural-language-processing", "annotations"], "urls": [], "use_cases": ["find NER training datasets for English", "get entity recognition corpora in other languages", "convert NER datasets to CoNLL 2003 format", "benchmark named entity recognition models on multiple corpora", "find domain-specific NER data like Twitter or Wikipedia text", "collect annotated data for sequence labeling research"], "what_it_is": "A curated collection of annotated corpora for named entity recognition (NER) and entity recognition tasks across multiple languages, domains, and entity types. It includes conversion code to the CoNLL 2003 format and links to datasets that cannot be redistributed due to licensing.", "when_to_avoid": ["you need recently published NER datasets after 2020, as the list is no longer actively updated", "you need the actual data for LDC-licensed corpora, which must be purchased separately", "you need a hosted dataset API rather than links and conversion scripts"], "when_to_choose": ["you need a catalog of NER corpora with licensing and availability info", "you want datasets pre-converted or convertible to CoNLL format", "you are comparing NER models across multiple benchmarks"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/entity-recognition-datasets", "repo": "juand-r/entity-recognition-datasets", "role": "main", "score": 73}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:05.772324+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:57:39.353391+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "111cb21c0fa535ef248be075b637569750c0faedde24e20b032551a5cce13c7c", "fetched_at": "2026-08-28T04:05:05.772324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juand-r/entity-recognition-datasets"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:05.772324+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:57:39.353391+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "111cb21c0fa535ef248be075b637569750c0faedde24e20b032551a5cce13c7c", "fetched_at": "2026-08-28T04:05:05.772324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juand-r/entity-recognition-datasets"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:57:39.353391+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "111cb21c0fa535ef248be075b637569750c0faedde24e20b032551a5cce13c7c", "fetched_at": "2026-08-28T04:05:05.772324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juand-r/entity-recognition-datasets"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:05.772324+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:05.772324+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:05.772324+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:57:39.353391+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "111cb21c0fa535ef248be075b637569750c0faedde24e20b032551a5cce13c7c", "fetched_at": "2026-08-28T04:05:05.772324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juand-r/entity-recognition-datasets"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:05.772324+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:05.772324+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:57:39.353391+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "111cb21c0fa535ef248be075b637569750c0faedde24e20b032551a5cce13c7c", "fetched_at": "2026-08-28T04:05:05.772324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juand-r/entity-recognition-datasets"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:05.772324+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:05.772324+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:05.772324+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:57:39.353391+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "111cb21c0fa535ef248be075b637569750c0faedde24e20b032551a5cce13c7c", "fetched_at": "2026-08-28T04:05:05.772324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juand-r/entity-recognition-datasets"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:05.772324+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:05.772324+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:57:39.353391+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "111cb21c0fa535ef248be075b637569750c0faedde24e20b032551a5cce13c7c", "fetched_at": "2026-08-28T04:05:05.772324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juand-r/entity-recognition-datasets"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:57:39.353391+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "111cb21c0fa535ef248be075b637569750c0faedde24e20b032551a5cce13c7c", "fetched_at": "2026-08-28T04:05:05.772324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juand-r/entity-recognition-datasets"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:57:39.353391+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "111cb21c0fa535ef248be075b637569750c0faedde24e20b032551a5cce13c7c", "fetched_at": "2026-08-28T04:05:05.772324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juand-r/entity-recognition-datasets"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:57:39.353391+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "111cb21c0fa535ef248be075b637569750c0faedde24e20b032551a5cce13c7c", "fetched_at": "2026-08-28T04:05:05.772324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juand-r/entity-recognition-datasets"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 90, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2923, "days_push": 62, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 73, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}