Triple

T14938708
Position Surface form Disambiguated ID Type / Status
Subject Harold Prince E372464 entity
Predicate notableWork P4 FINISHED
Object Follies E136794 NE FINISHED

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: Follies | Statement: [Harold Prince, notableWork, Follies]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Follies
Context triple: [Harold Prince, notableWork, Follies]
  • A. Follies chosen
    Follies is a celebrated Stephen Sondheim musical that nostalgically explores aging, memory, and lost dreams through a reunion of former showgirls in a crumbling Broadway theater.
  • B. Merrily We Roll Along
    Merrily We Roll Along is a 1981 Broadway musical with music and lyrics by Stephen Sondheim that traces the troubled lives and careers of three friends in reverse chronological order.
  • C. Merrily We Roll Along
    "Merrily We Roll Along" is a popular song best known as the iconic theme music for the classic Warner Bros. Looney Tunes cartoons.
  • D. Can-Can
    Can-Can is a 1953 Broadway musical by Cole Porter, best known for its lively Parisian setting and memorable score featuring songs like "I Love Paris."
  • E. Between Riverside and Crazy
    "Between Riverside and Crazy" is a Pulitzer Prize–winning dark comedy-drama play by Stephen Adly Guirgis that explores race, family, and gentrification through the story of a retired New York City cop fighting eviction from his rent-controlled apartment.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d85cc9da0c81908d583ca3f63a3908 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded64904d88190b6b4140da8e8199d completed April 15, 2026, 12:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe7e8e9c0c81909cfb1e02987527c0 completed May 9, 2026, 12:23 a.m.
Created at: April 10, 2026, 2:38 a.m.