Triple

T22981345
Position Surface form Disambiguated ID Type / Status
Subject Bill Gold E571472 entity
Predicate name P16 FINISHED
Object Bill Gold 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: Bill Gold | Statement: [Bill Gold, name, Bill Gold]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bill Gold
Context triple: [Bill Gold, name, Bill Gold]
  • A. Bill Gold chosen
    Bill Gold was a renowned American graphic designer best known for creating iconic movie posters for Hollywood films over several decades.
  • B. Mort Shuman
    Mort Shuman was an American songwriter and pianist best known for co-writing numerous 1960s pop and rock hits, including many for artists like Elvis Presley and The Drifters.
  • C. Mack David
    Mack David was an American lyricist and songwriter known for his popular song adaptations and contributions to film and television music.
  • D. Harold Rome
    Harold Rome was an American composer and lyricist best known for his work on Broadway musicals and film scores in the mid-20th century.
  • E. Jerry Livingston
    Jerry Livingston was an American songwriter and composer best known for his popular film and pop standards, including work on classic Disney songs.
  • 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_69e245b3c50481908bb3741ec9f40862 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1829589548190863619aebcae026c completed April 29, 2026, 4:01 a.m.
Created at: April 17, 2026, 3:49 p.m.