Triple

T8617231
Position Surface form Disambiguated ID Type / Status
Subject Lucille La Verne E204069 entity
Predicate voiceRole P12691 FINISHED
Object Evil Queen E173047 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: Evil Queen | Statement: [Lucille La Verne, voiceRole, Evil Queen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Evil Queen
Context triple: [Lucille La Verne, voiceRole, Evil Queen]
  • A. The Evil Queen chosen
    The Evil Queen is the vain and power-hungry royal villain from Disney’s Snow White, infamous for her jealousy and use of dark magic to eliminate her rival.
  • B. Carabosse
    Carabosse is the malevolent fairy or sorceress who curses Princess Aurora in the classic fairy tale and ballet "The Sleeping Beauty."
  • C. Queen Red
    Queen Red was one of the designated assault sub-sectors of Sword Beach used by Allied forces during the D-Day landings in World War II.
  • D. the Witch from Rapunzel
    The Witch from Rapunzel is the powerful, overprotective sorceress who imprisons Rapunzel in a tower and serves as the primary antagonist in the classic fairy tale.
  • E. Lady Tremaine
    Lady Tremaine is the cruel and calculating stepmother of Cinderella, best known as the primary antagonist in Disney’s 1950 animated film.
  • 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_69ca832ceab8819096e4a9f546695079 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cc4711c7748190af26ff5a78ef66a2 completed March 31, 2026, 10:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69cea923ae148190a973ef8ad6ccac9a completed April 2, 2026, 5:36 p.m.
Created at: March 30, 2026, 6:26 p.m.