Triple

T22451282
Position Surface form Disambiguated ID Type / Status
Subject Keller factory E554996 entity
Predicate createdBy P806 FINISHED
Object Arthur Miller 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: Arthur Miller | Statement: [Keller factory, createdBy, Arthur Miller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arthur Miller
Context triple: [Keller factory, createdBy, Arthur Miller]
  • A. Arthur Miller chosen
    Arthur Miller was a prominent 20th-century American playwright known for his socially critical dramas such as "Death of a Salesman" and "The Crucible."
  • B. Arthur R. Miller
    Arthur R. Miller is a prominent American legal scholar and professor, best known as a leading authority on civil procedure and complex litigation.
  • C. Arthur C. Miller
    Arthur C. Miller was an American cinematographer renowned for his work on numerous classic Hollywood films, including several Academy Award–winning productions.
  • D. Clifford Odets
    Clifford Odets was an influential American playwright and screenwriter associated with the Group Theatre, known for his socially conscious dramas and sharp, realistic dialogue.
  • E. Edward Albee
    Edward Albee was an influential American playwright best known for his sharp, psychologically intense dramas such as "Who's Afraid of Virginia Woolf?"
  • 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b4ba6a88190a0a79e2c20fa8c08 completed April 29, 2026, 1:13 a.m.
Created at: April 16, 2026, 8:48 p.m.