Triple

T3056295
Position Surface form Disambiguated ID Type / Status
Subject Hocus Pocus E60487 entity
Predicate character P662 FINISHED
Object Mary Sanderson E323391 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: Mary Sanderson | Statement: [Hocus Pocus, character, Mary Sanderson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Sanderson
Context triple: [Hocus Pocus, character, Mary Sanderson]
  • A. Mary Sanderson chosen
    Mary Sanderson is one of the three comedic witch sisters in the fantasy film "Hocus Pocus," known for her quirky personality and keen sense of smell for tracking children.
  • B. Magdalene Shaw
    Magdalene Shaw is a sharp-witted, tough matriarch and career criminal in the Fast & Furious franchise, known as the mother of Deckard and Owen Shaw.
  • C. Susannah Harker
    Susannah Harker is a British actress best known for her television work in period dramas and series such as "House of Cards" and "Pride and Prejudice."
  • D. Emma Sandys
    Emma Sandys was a 19th-century British painter associated with the Pre-Raphaelite movement, known for her richly detailed portraits of women and children.
  • E. Dolly Sharp
    Dolly Sharp was an American adult film actress best known for her role in the landmark 1972 pornographic film "Deep Throat."
  • 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_69ad8578137c81908259dcb27c7d6d7c completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ad9bf7ebd48190ad5748a18fa9a56a completed March 8, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1f8759f988190a69ca8a4682af5ba completed March 11, 2026, 11:19 p.m.
Created at: March 8, 2026, 3:02 p.m.