Triple

T1009973
Position Surface form Disambiguated ID Type / Status
Subject Harry Potter and the Deathly Hallows – Part 2 E21798 entity
Predicate castMember P1668 FINISHED
Object Bonnie Wright E126332 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: Bonnie Wright | Statement: [Harry Potter and the Deathly Hallows – Part 2, castMember, Bonnie Wright]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bonnie Wright
Context triple: [Harry Potter and the Deathly Hallows – Part 2, castMember, Bonnie Wright]
  • A. Bonnie Wright chosen
    Bonnie Wright is an English actress and filmmaker best known for playing Ginny Weasley in the Harry Potter film series.
  • B. Evanna Lynch
    Evanna Lynch is an Irish actress best known for playing Luna Lovegood in the Harry Potter film series.
  • C. Miranda Otto
    Miranda Otto is an Australian actress best known for playing Éowyn in Peter Jackson’s The Lord of the Rings film trilogy.
  • D. Joanna Blunt
    Joanna Blunt is the mother of British actress Emily Blunt and a member of the Blunt family connected to the entertainment industry.
  • E. Sadie Frost
    Sadie Frost is an English actress, producer, and fashion designer known for her roles in films like "Bram Stoker's Dracula" and for co-founding the fashion label Frost French.
  • 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_69a493c68e24819080ed0ee8bcfd5ce0 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b7a3cb608190a2de34a09cd55146 completed March 1, 2026, 10:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac5995ad6c8190a324094151442bce completed March 7, 2026, 5 p.m.
Created at: March 1, 2026, 7:41 p.m.