Triple

T18707646
Position Surface form Disambiguated ID Type / Status
Subject Fanny by Gaslight E457414 entity
Predicate castMember P1668 FINISHED
Object John Laurie 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: John Laurie | Statement: [Fanny by Gaslight, castMember, John Laurie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Laurie
Context triple: [Fanny by Gaslight, castMember, John Laurie]
  • A. John Laurie chosen
    John Laurie was a Scottish actor best known for his roles in classic British films and for playing Private Frazer in the television series "Dad's Army."
  • B. Frank Shepard
    Frank Shepard was an American legal publisher and innovator best known for developing the Shepard's Citations system used to track the subsequent history and treatment of legal cases.
  • C. Kurt Farquhar
    Kurt Farquhar is an American television and film composer known for scoring numerous popular series, particularly in comedy and drama.
  • D. Albert Hadley
    Albert Hadley was a prominent American interior designer renowned for his influential partnership with Sister Parish and his refined, modern classic style.
  • E. Frank Mauro
    Frank Mauro is a musician known for being a member of the influential New York punk band Richard Hell and the Voidoids.
  • 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_69d8d392aad081909fe31aa03e6e97d1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e567185c648190848ca47498eb56b3 completed April 19, 2026, 11:36 p.m.
Created at: April 10, 2026, 11:50 a.m.