Triple

T19199922
Position Surface form Disambiguated ID Type / Status
Subject Sam Cooke E470077 entity
Predicate recordLabel P1500 FINISHED
Object Keen 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: Keen Records | Statement: [Sam Cooke, recordLabel, Keen Records]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keen Records
Context triple: [Sam Cooke, recordLabel, Keen Records]
  • A. Keen Records chosen
    Keen Records was an American independent record label best known for releasing some of Sam Cooke’s early and most influential soul recordings in the late 1950s.
  • B. Keynote Records
    Keynote Records was an American record label active in the 1940s, best known for its folk and early jazz recordings, including politically oriented releases by groups like the Almanac Singers.
  • C. Tayberry Records
    Tayberry Records is an independent music label associated with the North Hills music scene.
  • D. Koch Records
    Koch Records is an independent American record label known for distributing and promoting a wide range of hip-hop and urban music artists.
  • E. Regal Recordings
    Regal Recordings is a British record label known for signing prominent artists such as Lily Allen and releasing influential pop and alternative music.
  • 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_69d8dd0ad9088190a173b32657ae2e7a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f9967ac081909106aa5ea447e94d completed April 20, 2026, 10:01 a.m.
Created at: April 10, 2026, 12:07 p.m.