Triple

T22472177
Position Surface form Disambiguated ID Type / Status
Subject Jeff Richards E555528 entity
Predicate workedWith P398 FINISHED
Object Howard Keel 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: Howard Keel | Statement: [Jeff Richards, workedWith, Howard Keel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Howard Keel
Context triple: [Jeff Richards, workedWith, Howard Keel]
  • A. Howard Keel chosen
    Howard Keel was an American actor and baritone singer best known for his leading roles in classic MGM musicals of the 1950s and later for his role on the TV series "Dallas."
  • B. Bob Merrill
    Bob Merrill was an American songwriter and lyricist best known for his work on Broadway musicals and popular songs in the mid-20th century.
  • C. Gordon MacRae
    Gordon MacRae was an American actor and singer best known for his leading roles in classic Hollywood film musicals such as "Oklahoma!" and "Carousel."
  • D. John Cullum
    John Cullum is an American actor and singer best known for his Tony Award–winning work on Broadway and his roles in film and television, including the series "Northern Exposure."
  • E. Cliff Hayes
    Cliff Hayes is a film editor best known for his work on the influential Australian action film "Mad Max."
  • 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_69e11e52c2048190952dc5df209b9bed completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15be0d3c08190851537660cda619c completed April 29, 2026, 1:16 a.m.
Created at: April 16, 2026, 8:48 p.m.