Triple

T18283135
Position Surface form Disambiguated ID Type / Status
Subject Ashildr E437912 entity
Predicate portrayedBy P1507 FINISHED
Object Maisie Williams NE NERFINISHED

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: Maisie Williams | Statement: [Ashildr, portrayedBy, Maisie Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maisie Williams
Context triple: [Ashildr, portrayedBy, Maisie Williams]
  • A. Maisie Williams chosen
    Maisie Williams is an English actress best known for her breakout role as Arya Stark in the television series "Game of Thrones."
  • B. Bella Ramsey
    Bella Ramsey is an English actor best known for their breakout role as Lyanna Mormont in "Game of Thrones" and for playing Ellie in HBO's adaptation of "The Last of Us."
  • C. Alexandra Astin
    Alexandra Astin is an American actress and the daughter of actor Sean Astin, known for her small role in "The Lord of the Rings: The Return of the King."
  • D. Emilia Clarke
    Emilia Clarke is an English actress best known for her role as Daenerys Targaryen in the television series "Game of Thrones."
  • E. Saskia Reeves
    Saskia Reeves is a British actress known for her work in film, television, and theatre, including roles in series such as "Luther" and numerous acclaimed stage productions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b914530c8190b4474d862a2b2a1b completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50057c5c881909fcda72f4a98c8c3 completed April 19, 2026, 4:18 p.m.
Created at: April 10, 2026, 10:35 a.m.