Triple

T21881475
Position Surface form Disambiguated ID Type / Status
Subject Christopher Ashley E540290 entity
Predicate directed P7373 FINISHED
Object Diana (musical) 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: Diana (musical) | Statement: [Christopher Ashley, directed, Diana (musical)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diana (musical)
Context triple: [Christopher Ashley, directed, Diana (musical)]
  • A. Diana (musical) chosen
    Diana is a Broadway musical that dramatizes the life and legacy of Diana, Princess of Wales, featuring music by Bon Jovi keyboardist David Bryan.
  • B. The Rest of Diana
    The Rest of Diana is an 18th-century mythological painting by French Rococo artist Carle Van Loo depicting the Roman goddess Diana in a moment of repose.
  • C. Torch Song
    "Torch Song" is a 1953 American musical drama film starring Joan Crawford as a demanding Broadway star whose life and career are challenged by a blind pianist.
  • D. Broadway Rose
    Broadway Rose is a silent-era film featuring Mae Murray, showcasing her as a glamorous star of early American cinema.
  • E. Broadway Girls
    "Broadway Girls" is a 2021 country-trap fusion single by rapper Lil Durk featuring country artist Morgan Wallen that became a viral hit on streaming platforms.
  • 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_69e0c479a98081908ce333853fdd4348 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f118e7a3c48190be1cc285ad4b6496 completed April 28, 2026, 8:30 p.m.
Created at: April 16, 2026, 7:04 p.m.