Triple

T20561842
Position Surface form Disambiguated ID Type / Status
Subject Ken Kercheval E504860 entity
Predicate residence P75 FINISHED
Object Indiana, United States 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: Indiana, United States | Statement: [Ken Kercheval, residence, Indiana, United States]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Indiana, United States
Context triple: [Ken Kercheval, residence, Indiana, United States]
  • A. Indiana chosen
    Indiana is a U.S. state known for its manufacturing base, rich agricultural land, and iconic events like the Indianapolis 500.
  • B. Indiana
    "Indiana" is a jazz standard widely performed and recorded by saxophonist Don Byas, showcasing his virtuosic improvisational style.
  • C. Indiana, Pennsylvania, United States
    Indiana, Pennsylvania, United States, is a small borough in western Pennsylvania best known as the hometown of actor James Stewart and for its historic downtown and university presence.
  • D. Illinois and Indiana
    Illinois and Indiana are neighboring Midwestern U.S. states whose shared boundary is partly defined by the Ohio River.
  • E. Ohio, Illinois
    Ohio, Illinois is a small rural village in Bureau County known for its agricultural surroundings and quiet small-town character.
  • 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_69e0b4b6587c8190aee63dc7cff244ea completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a79ec10481909740eb6a08ae2658 completed April 20, 2026, 10:24 p.m.
Created at: April 16, 2026, 11:39 a.m.