Triple

T799319
Position Surface form Disambiguated ID Type / Status
Subject Tennessee E17093 entity
Predicate bordersState P224 FINISHED
Object Kentucky E18292 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Kentucky | Statement: [Tennessee, bordersState, Kentucky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kentucky
Context triple: [Tennessee, bordersState, Kentucky]
  • A. Kentucky chosen
    Kentucky is a southeastern U.S. state known for its horse racing, bourbon distilleries, bluegrass music, and diverse landscapes ranging from Appalachian mountains to fertile river valleys.
  • B. Tennessee
    Tennessee is a southeastern U.S. state known for its diverse landscapes from the Appalachian Mountains to the Mississippi River, and for major cultural centers like Nashville and Memphis that have shaped American music and history.
  • C. West Virginia
    West Virginia is a landlocked, mountainous U.S. state in the Appalachian region, known for its coal mining history, outdoor recreation, and distinct cultural heritage.
  • D. Arkansas
    Arkansas is a landlocked state in the southern United States known for its diverse geography, including the Ozark and Ouachita Mountains, forests, and fertile plains.
  • E. Indiana
    Indiana is a U.S. state known for its manufacturing base, rich agricultural land, and iconic events like the Indianapolis 500.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a49378b9c48190adbf5f62e5b7aca1 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a7cb26dc8190bdd3a278b8695873 completed March 1, 2026, 8:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69acaca531348190b47f98bc825b1307 completed March 7, 2026, 10:54 p.m.
Created at: March 1, 2026, 7:38 p.m.