Triple

T20569148
Position Surface form Disambiguated ID Type / Status
Subject Topeka Regional Airport E505043 entity
Predicate servesRegion P82 FINISHED
Object Shawnee County 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: Shawnee County | Statement: [Topeka Regional Airport, servesRegion, Shawnee County]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shawnee County
Context triple: [Topeka Regional Airport, servesRegion, Shawnee County]
  • A. Shawnee County, Kansas chosen
    Shawnee County, Kansas is a county in northeastern Kansas that includes the state capital, Topeka, as its county seat and largest city.
  • B. Johnson County
    Johnson County is a county in northeastern Kansas that includes suburban communities within the Kansas City metropolitan area.
  • C. Johnson County
    Johnson County is a county in north-central Texas that includes part of the Dallas–Fort Worth metropolitan area and encompasses cities such as Mansfield.
  • D. Johnson County
    Johnson County is a suburban county in central Indiana that forms part of the greater Indianapolis metropolitan region.
  • E. Johnson County
    Johnson County is a county in west-central Missouri whose seat and largest city is Warrensburg.
  • 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_69e0b4b721588190993ac7b0a9be2736 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a7a4b90c81909854dac72f671eec completed April 20, 2026, 10:24 p.m.
Created at: April 16, 2026, 11:39 a.m.