Triple

T21822057
Position Surface form Disambiguated ID Type / Status
Subject UCLA Bruins men's volleyball E538750 entity
Predicate headCoach P256 FINISHED
Object John Speraw 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: John Speraw | Statement: [UCLA Bruins men's volleyball, headCoach, John Speraw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Speraw
Context triple: [UCLA Bruins men's volleyball, headCoach, John Speraw]
  • A. John Speraw chosen
    John Speraw is an American volleyball coach best known for leading the U.S. men’s national team and achieving success at both the international and collegiate levels.
  • B. Greg Grabianski
    Greg Grabianski is a screenwriter best known for his work on the parody horror-comedy film "Scary Movie 2."
  • C. Christopher Sweeney
    Christopher Sweeney is a music video director known for his work on high-profile pop and alternative artists’ videos, including Lily Allen’s “Hard Out Here.”
  • D. Charles Ardai
    Charles Ardai is an American writer, editor, and entrepreneur best known as the founder of the Hard Case Crime imprint and for his award-winning crime and mystery fiction.
  • E. Stephen Shepard
    Stephen Shepard is an American journalist and magazine editor best known as the former editor-in-chief of BusinessWeek and founding dean of the CUNY Graduate School of Journalism.
  • 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_69e0c475038c8190abb9b1a20eb8ff50 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f0912e432481909045d00a61daa767 completed April 28, 2026, 10:51 a.m.
Created at: April 16, 2026, 6:54 p.m.