Triple

T22606170
Position Surface form Disambiguated ID Type / Status
Subject Durant Regional Airport – Eaker Field E566564 entity
Predicate serves P98 FINISHED
Object Durant, Oklahoma 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: Durant, Oklahoma | Statement: [Durant Regional Airport – Eaker Field, serves, Durant, Oklahoma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Durant, Oklahoma
Context triple: [Durant Regional Airport – Eaker Field, serves, Durant, Oklahoma]
  • A. Durant, Oklahoma chosen
    Durant, Oklahoma is a small city in southeastern Oklahoma known as the "Magnolia Capital of Oklahoma" and serves as a regional hub near the Texas border and Lake Texoma.
  • B. Johnson, Oklahoma
    Johnson, Oklahoma is a small unincorporated community located in Pottawatomie County in the central part of the state.
  • C. Dewey, Oklahoma
    Dewey, Oklahoma is a small city in northeastern Oklahoma known for its historic downtown and the Tom Mix Museum.
  • D. Washington, Oklahoma
    Washington, Oklahoma is a small town in central Oklahoma known for its rural community character and local school system.
  • E. Wilson, Oklahoma
    Wilson, Oklahoma is a small rural city in southern Oklahoma known for its tight-knit community and location within Carter County.
  • 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_69e245884860819081046ce07d5872c4 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1627172488190beb87df965498bcc completed April 29, 2026, 1:44 a.m.
Created at: April 17, 2026, 2:54 p.m.