Données structurées de l’entrée pour les outils humains, les systèmes IA et les clients machine.
{
"@context": [
"https://schema.org",
{
"lxw": "https://lxkeys.world/schema/"
}
],
"@type": "Thing",
"identifier": "ENT-00002047",
"name": "Penn Treebank",
"alternateName": [],
"additionalType": {
"category": "Data and Evaluation",
"type": "Dataset",
"subtype": "",
"lxkeysEntity": false
},
"description": "Penn Treebank is a dataset associated with LDC, classified in LXKeys.world as AI Dataset.",
"creator": "Linguistic Data Consortium",
"url": "https://lxkeys.world/entry.php?id=ENT-00002047&lang=fr",
"sameAs": "https://catalog.ldc.upenn.edu/LDC99T42",
"image": "",
"lxkeysWorld": {
"worldId": "ENT-00002047",
"kind": "Data and Evaluation",
"type": "Dataset",
"subtype": "",
"classification": "AI Dataset",
"organization": "LDC",
"originContext": "AI evaluation and data infrastructure",
"firstPublicAppearance": "1993",
"currentStatus": "Active",
"documentationStatus": "Documented",
"documentationIndex": {
"total": 88,
"documentation": 25,
"evidence": 13,
"structure": 25,
"relationships": 25,
"level": "Level V Persistent"
},
"lxCalendarium": {
"start_date_utc": "2023-04-01",
"created_utc": "2026-06-17T01:33:48+00:00",
"created_dypclt": "D-0 Y-2 P-3 C-3 L-22 T-4",
"updated_utc": "2026-06-17T01:33:48+00:00",
"updated_dypclt": "D-0 Y-2 P-3 C-3 L-22 T-4"
},
"facts": [],
"capabilities": [
"Evaluation resource for AI systems",
"Dataset or benchmark documentation",
"Machine-learning task reference",
"Source-linked registry metadata",
"Relationship graph compatibility"
],
"limitations": [
"Coverage and licensing should be interpreted through the linked source record.",
"Benchmark scores or dataset contents can evolve over time through external updates."
],
"tags": [
"Dataset",
"Benchmark",
"Evaluation",
"Data Resource"
],
"timeline": [
{
"date": "1993",
"title": "Initial dataset release",
"description": "Penn Treebank entered the documented public record in 1993. This event is retained at the precision supported by the Entry’s reviewed source history.",
"source_url": "https://catalog.ldc.upenn.edu/LDC99T42",
"verification_status": "source_backed_official"
}
],
"relationships": [
{
"target": "Linguistic Data Consortium",
"type": "Creator",
"description": "Linguistic Data Consortium is documented as creator, contributor or originating team for Penn Treebank.",
"evidence_level": "documentary"
},
{
"target": "LDC",
"type": "Associated organization",
"description": "LDC is the organization or institutional context associated with Penn Treebank.",
"evidence_level": "documentary"
},
{
"target": "Evaluation / Data Resource",
"type": "Classification",
"description": "Penn Treebank is classified as Evaluation / Data Resource.",
"evidence_level": "documentary"
}
],
"sources": [
{
"label": "Official documentation",
"url": "https://catalog.ldc.upenn.edu/LDC99T42",
"source_type": "Reference Source",
"verification_status": "verified",
"authority": "OFFICIAL",
"role": "primary",
"update_enabled": true,
"authority_basis": "curated-corpus-refresh-2026-09-08"
}
],
"canonical": [],
"imageMeta": []
}
}