Triple

T6345727
Position Surface form Disambiguated ID Type / Status
Subject Benny Goodman E142738 entity
Predicate associatedAct P37 FINISHED
Object Harry James E549257 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: Harry James | Statement: [Benny Goodman, associatedAct, Harry James]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry James
Context triple: [Benny Goodman, associatedAct, Harry James]
  • A. Harry James chosen
    Harry James was a renowned American jazz trumpeter and bandleader celebrated for his virtuosic playing and popularity during the big band era.
  • B. Harry Bruce
    Harry Bruce was an Australian politician and public figure after whom Queensland’s major Bruce Highway is named.
  • C. Hal James
    Hal James was a theatrical producer best known for his work on the acclaimed Broadway musical "Man of La Mancha."
  • D. Harrison James
    Harrison James is a prominent Canadian ballet dancer recognized for his leading performances with the National Ballet of Canada.
  • E. Billy James
    Billy James is a musician best known for composing the soundtrack to the 1971 road movie "Two-Lane Blacktop."
  • 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_69c008d5ab108190b346c465696824a9 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c067b7e0d08190abacaf41c08ed15e completed March 22, 2026, 10:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69c604454fd48190972476a0929dfb9d completed March 27, 2026, 4:15 a.m.
Created at: March 22, 2026, 4:31 p.m.