Triple

T20305669
Position Surface form Disambiguated ID Type / Status
Subject Gordon Jenkins E505602 entity
Predicate employer P7 FINISHED
Object Decca Records 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: Decca Records | Statement: [Gordon Jenkins, employer, Decca Records]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Decca Records
Context triple: [Gordon Jenkins, employer, Decca Records]
  • A. Decca Records chosen
    Decca Records is a historic British record label renowned for its influential catalog across jazz, classical, and popular music, having recorded major artists such as Louis Armstrong.
  • B. EMI Records
    EMI Records was a major British record label and music company known for its influential roster of artists and significant impact on the global recording industry.
  • C. Phonogram Records
    Phonogram Records was a major international record label active in the 1970s and 1980s, known for releasing rock and pop music by prominent artists in Europe and beyond.
  • D. Savoy Records
    Savoy Records is a pioneering American jazz and blues record label renowned for recording influential bebop artists such as Charlie Parker.
  • E. RCA Victor
    RCA Victor was a major American record label and phonograph company, historically significant for its role in the development and popularization of recorded music and audio technology.
  • 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_69e0b4b8ab648190906e18538c250148 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6773f8f688190b616f972b9bbb28e completed April 20, 2026, 6:58 p.m.
Created at: April 16, 2026, 11:18 a.m.