Triple

T20768469
Position Surface form Disambiguated ID Type / Status
Subject U.S. Route 31E E511162 entity
Predicate connectsCity P4245 FINISHED
Object Glasgow, 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: Glasgow, Kentucky | Statement: [U.S. Route 31E, connectsCity, Glasgow, Kentucky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Glasgow, Kentucky
Context triple: [U.S. Route 31E, connectsCity, Glasgow, Kentucky]
  • A. Glasgow, Kentucky chosen
    Glasgow, Kentucky is a small city in Barren County known as a regional hub for commerce and healthcare in south-central Kentucky.
  • B. Kingston, Kentucky
    Kingston, Kentucky is a small unincorporated community in Madison County that lies between Richmond and Berea in central Kentucky.
  • C. Melbourne, Kentucky
    Melbourne, Kentucky is a small city in northern Kentucky situated along the Ohio River within the Cincinnati metropolitan area.
  • D. Graham, Kentucky
    Graham, Kentucky is a small unincorporated rural community located in Muhlenberg County in the western part of the state.
  • E. Southgate, Kentucky
    Southgate, Kentucky is a small suburban city in northern Kentucky, located just south of Cincinnati and known for its residential character and proximity to major urban amenities.
  • 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_69e0b4ca01148190ac018e57e0cab46f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c24fa1b08190b09ab8fcb87b5c01 completed April 21, 2026, 12:18 a.m.
Created at: April 16, 2026, 12:36 p.m.