Triple

T19899308
Position Surface form Disambiguated ID Type / Status
Subject Campbellsville, Kentucky E478237 entity
Predicate hasNearbyCity P350 FINISHED
Object Lebanon, Kentucky 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: Lebanon, Kentucky | Statement: [Campbellsville, Kentucky, hasNearbyCity, Lebanon, Kentucky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lebanon, Kentucky
Context triple: [Campbellsville, Kentucky, hasNearbyCity, Lebanon, Kentucky]
  • A. Lebanon, Kentucky chosen
    Lebanon, Kentucky is a small city in central Kentucky that serves as the county seat of Marion County and is known for its historic downtown and bourbon-related attractions.
  • B. Liberty, Kentucky
    Liberty, Kentucky is a small rural city in south-central Kentucky that serves as the administrative and commercial hub of Casey County.
  • C. Hardin, Kentucky
    Hardin, Kentucky is a small rural city located in Marshall County in western Kentucky.
  • D. Crittenden, Kentucky
    Crittenden, Kentucky is a small city in northern Kentucky that serves as a residential community within the Cincinnati metropolitan area.
  • E. Murray, Kentucky
    Murray, Kentucky is a small city in southwestern Kentucky best known as the home of Murray State University and for its strong college-town atmosphere.
  • 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_69d8e520682081909892916424699bd5 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6593fbb348190afa7acf45af406ed completed April 20, 2026, 4:50 p.m.
Created at: April 10, 2026, 1:52 p.m.