Triple

T22101290
Position Surface form Disambiguated ID Type / Status
Subject The Maggie E546176 entity
Predicate castMember P1668 FINISHED
Object Catherine Lacey 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: Catherine Lacey | Statement: [The Maggie, castMember, Catherine Lacey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Catherine Lacey
Context triple: [The Maggie, castMember, Catherine Lacey]
  • A. Catherine Lacey chosen
    Catherine Lacey was a British character actress known for her prolific work in mid-20th-century film, television, and theatre, often portraying sharp-tongued or eccentric older women.
  • B. Sara Quin
    Sara Quin is a Canadian musician best known as one half of the indie pop duo Tegan and Sara.
  • C. Augusta Read Thomas
    Augusta Read Thomas is an acclaimed American composer known for her vibrant, lyrical contemporary classical works and significant contributions to modern orchestral and chamber music.
  • D. Lauren Groff
    Lauren Groff is an acclaimed contemporary American novelist and short story writer known for works such as "Fates and Furies," "Matrix," and "Florida."
  • E. Vendela Vida
    Vendela Vida is an American novelist, editor, and screenwriter known for her literary fiction and for co-founding the publishing house McSweeney’s.
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1291501508190ad5689be5abb2ba6 completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.