Triple

T20075223
Position Surface form Disambiguated ID Type / Status
Subject Eddyville, Kentucky E499844 entity
Predicate locatedOn P40 FINISHED
Object Kentucky Lake NE NERFINISHED

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 Lake | Statement: [Eddyville, Kentucky, locatedOn, Kentucky Lake]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kentucky Lake
Context triple: [Eddyville, Kentucky, locatedOn, Kentucky Lake]
  • A. Kentucky Lake chosen
    Kentucky Lake is a large man-made reservoir in western Kentucky and Tennessee, popular for boating, fishing, and recreation and known as one of the largest artificial lakes in the eastern United States.
  • B. Cherokee Lake
    Cherokee Lake is a large reservoir in eastern Tennessee popular for boating, fishing, and lakeside recreation.
  • C. Harlan County Lake
    Harlan County Lake is a large reservoir in south-central Nebraska known for flood control, irrigation storage, and outdoor recreation such as fishing and boating.
  • D. J. Percy Priest Lake
    J. Percy Priest Lake is a large man-made reservoir near Nashville, Tennessee, popular for boating, fishing, and other outdoor recreation.
  • E. Walton Lake
    Walton Lake is a small freshwater lake located in the town of Monroe in Orange County, New York, popular for local recreation and scenic views.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6643ab0448190ab18d013b72aaf32 completed April 20, 2026, 5:36 p.m.
Created at: April 11, 2026, 3:40 p.m.