Triple

T22032268
Position Surface form Disambiguated ID Type / Status
Subject Uniontown, Kansas E544113 entity
Predicate hasOfficialName P66 FINISHED
Object Uniontown, Kansas 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: Uniontown, Kansas | Statement: [Uniontown, Kansas, hasOfficialName, Uniontown, Kansas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Uniontown, Kansas
Context triple: [Uniontown, Kansas, hasOfficialName, Uniontown, Kansas]
  • A. Uniontown, Kansas chosen
    Uniontown, Kansas is a small rural city located in southeastern Kansas within Bourbon County.
  • B. Union Township, Kansas
    Union Township, Kansas is a rural civil township located within McPherson County in the central part of the state.
  • C. Mapleton, Kansas
    Mapleton, Kansas is a small rural town located in Bourbon County in southeastern Kansas, United States.
  • D. Plainville, Kansas
    Plainville, Kansas is a small city in north-central Kansas that serves as the primary population and commercial center of Rooks County.
  • E. Belvue, Kansas
    Belvue, Kansas is a small rural city in Pottawatomie County that functions as part of the greater Manhattan, Kansas regional community.
  • 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_69e11e2f98c8819083e11eab90942a78 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127ee84848190a22c24bf14498520 completed April 28, 2026, 9:34 p.m.
Created at: April 16, 2026, 8:24 p.m.