Triple

T6702677
Position Surface form Disambiguated ID Type / Status
Subject Harvard-Westlake School E152917 entity
Predicate hasNotableAlumni P51 FINISHED
Object Jason Collins E459303 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: Jason Collins | Statement: [Harvard-Westlake School, hasNotableAlumni, Jason Collins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jason Collins
Context triple: [Harvard-Westlake School, hasNotableAlumni, Jason Collins]
  • A. Jason Collins chosen
    Jason Collins is a retired American professional basketball player best known for becoming the first openly gay active player in the NBA.
  • B. Benjamin Everett Jordan
    Benjamin Everett Jordan was a mid-20th-century Democratic U.S. Senator from North Carolina known for his influence on agricultural and textile policy.
  • C. Michael Bennett
    Michael Bennett was an influential American theater director and choreographer best known for shaping the modern Broadway musical with works like "A Chorus Line."
  • D. Jamar Beasley
    Jamar Beasley is an American former professional soccer and arena football player who was one of the early U.S. teenagers to turn pro in MLS.
  • E. Thomas Robinson
    Thomas Robinson was the son of Irish astronomer and physicist John Thomas Romney Robinson.
  • 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_69c68807adbc8190b8632df42b39eda0 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d0e5eb0c81908c4fa3febd2d23ca completed March 27, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69c70083e1948190b5ee3fffb9783531 completed March 27, 2026, 10:11 p.m.
Created at: March 27, 2026, 2:06 p.m.