Triple

T30767058
Position Surface form Disambiguated ID Type / Status
Subject Olivier Award for Best Revival for "After the Dance" (as director of the production) E783402 entity
Predicate authorOfWorkAwarded P25299 FINISHED
Object Terence Rattigan 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: Terence Rattigan | Statement: [Olivier Award for Best Revival for "After the Dance" (as director of the production), authorOfWorkAwarded, Terence Rattigan]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: authorOfWorkAwarded
Context triple: [Olivier Award for Best Revival for "After the Dance" (as director of the production), authorOfWorkAwarded, Terence Rattigan]
  • A. authorAwardedForBodyOfWork
    Indicates that an author received an award recognizing their entire body of work rather than a single specific piece.
  • B. literaryAwardedBy
    Indicates that a literary award is given or conferred by a particular person, organization, or institution.
  • C. recipientOfAward
    Indicates that an entity has received or been granted a particular award.
  • D. awardedAuthor chosen
    Indicates that an author has received an award or recognition.
  • E. namedAfterAwardLaureateOf
    Indicates that one entity is named after a person who is a laureate (recipient) of a particular award.
  • F. None of above.

Provenance (3 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_69f224b047f48190b4f5efeb7ee97b37 completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69fcec5f8b448190b48330a19b462d24 completed May 7, 2026, 7:47 p.m.
PD Predicate disambiguation batch_69fceaf1e23881908ca24160a638e329 completed May 7, 2026, 7:41 p.m.
Created at: April 29, 2026, 8:40 p.m.