Triple

T23230021
Position Surface form Disambiguated ID Type / Status
Subject Kirkland College E581123 entity
Predicate locatedIn P40 FINISHED
Object Clinton, New York 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: Clinton, New York | Statement: [Kirkland College, locatedIn, Clinton, New York]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Clinton, New York
Context triple: [Kirkland College, locatedIn, Clinton, New York]
  • A. Clinton, New York chosen
    Clinton, New York is a small village in Oneida County known for its historic charm and as the home of Hamilton College.
  • B. Wilson, New York
    Wilson, New York is a small town in Niagara County known for its location along Lake Ontario and its rural, lakeside character.
  • C. Jackson, New York
    Jackson, New York is a small rural town in Washington County known for its agricultural landscape and historic countryside in eastern upstate New York.
  • D. Roosevelt, New York
    Roosevelt, New York is a predominantly residential hamlet and census-designated place in Nassau County on Long Island, known for its diverse community and suburban character.
  • E. Hamilton, New York
    Hamilton, New York is a small village in Madison County best known as the home of Colgate University.
  • 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_69e246043c48819089bae72c9a9c306c completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f1923131c081909c6e84b1a0c32e0d completed April 29, 2026, 5:08 a.m.
Created at: April 17, 2026, 4:09 p.m.