Triple

T12496775
Position Surface form Disambiguated ID Type / Status
Subject Kearns, Utah E298710 entity
Predicate namedAfter P63 FINISHED
Object Thomas Kearns E707010 NE FINISHED

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: Thomas Kearns | Statement: [Kearns, Utah, namedAfter, Thomas Kearns]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Kearns
Context triple: [Kearns, Utah, namedAfter, Thomas Kearns]
  • A. Thomas Kearns chosen
    Thomas Kearns was a prominent American mining magnate, U.S. Senator from Utah, and influential businessman in the late 19th and early 20th centuries.
  • B. Gerald Kean
    Gerald Kean is a prominent Irish solicitor and media personality known for his high-profile legal work and frequent appearances in Irish popular culture.
  • C. James Kearns
    James Kearns is an American screenwriter best known for writing the 2002 crime thriller film "John Q."
  • D. Tom Kahn
    Tom Kahn was an American social democrat and civil rights activist known for his work with the AFL-CIO and his role in organizing the 1963 March on Washington.
  • E. Richard Parsons
    Richard Parsons is an American business executive best known for leading Time Warner as CEO in the early 2000s, including steering the company through the aftermath of its troubled merger with AOL.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6ada4cd388190ae3bbf83ff87057a completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94df948308190ace333230a4a3b38 completed April 10, 2026, 7:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64baf73188190af29b57f8ae9253f completed May 2, 2026, 7:08 p.m.
Created at: April 8, 2026, 9:57 p.m.