Triple

T17171670
Position Surface form Disambiguated ID Type / Status
Subject Annaleigh Ashford E416748 entity
Predicate notableWork P4 FINISHED
Object Wicked E116452 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: Wicked | Statement: [Annaleigh Ashford, notableWork, Wicked]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wicked
Context triple: [Annaleigh Ashford, notableWork, Wicked]
  • A. Wicked
    Wicked is a component or segment of the larger work "Necessary Evil," likely representing a distinct chapter, episode, or storyline within that overarching title.
  • B. Wicked
    Wicked is a 1998 psychological thriller film starring Vanessa Zima as a troubled teenager entangled in murder and obsession.
  • C. WICKED
    WICKED is the powerful and morally ambiguous organization in James Dashner’s Maze Runner series that conducts brutal experiments on teenagers in a desperate attempt to find a cure for a global disease.
  • D. Wicked (musical) chosen
    Wicked is a hit Broadway musical that reimagines the backstory of the witches from "The Wizard of Oz," featuring music and lyrics by Stephen Schwartz and a book by Winnie Holzman.
  • E. Wicked Part One
    Wicked Part One is the first installment of a two-part film adaptation of the hit Broadway musical "Wicked," exploring the untold story of the witches of Oz.
  • 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_69d886d5f34c8190b24564dfaa63f3fb completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3fc0ac22481909e992bb3a6ba36ad completed April 18, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_6a015fc83984819098c98b75cf021e3a completed May 11, 2026, 4:49 a.m.
Created at: April 10, 2026, 5:37 a.m.