Triple

T23226791
Position Surface form Disambiguated ID Type / Status
Subject The Big Broadcast of 1936 E581036 entity
Predicate screenwriter P2831 FINISHED
Object Howard J. Green 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 J. Green | Statement: [The Big Broadcast of 1936, screenwriter, Howard J. Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Howard J. Green
Context triple: [The Big Broadcast of 1936, screenwriter, Howard J. Green]
  • A. Howard J. Green chosen
    Howard J. Green was an American screenwriter active during Hollywood’s early sound era, known for his work on several prominent 1930s films.
  • B. Bernard L. Green
    Bernard L. Green was an architect known for designing the building known as The Big House.
  • C. Edward B. Green
    Edward B. Green was an American architect known for designing prominent public and institutional buildings in the early 20th century, particularly in Buffalo, New York.
  • D. W. Howard Greene
    W. Howard Greene was an American cinematographer noted for his pioneering work in early Technicolor films and multiple Academy Award–recognized achievements in color cinematography.
  • E. Gerald B. Greenberg
    Gerald B. Greenberg is an American film editor best known for his Academy Award–winning work on the 1979 drama "Kramer vs. Kramer."
  • 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_69e246043c48819089bae72c9a9c306c completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f1922f5b4081908145d66ea7534493 completed April 29, 2026, 5:07 a.m.
Created at: April 17, 2026, 4:09 p.m.