Triple

T6362722
Position Surface form Disambiguated ID Type / Status
Subject Vera Drake E143148 entity
Predicate castMember P1668 FINISHED
Object Eddie Marsan E89622 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: Eddie Marsan | Statement: [Vera Drake, castMember, Eddie Marsan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eddie Marsan
Context triple: [Vera Drake, castMember, Eddie Marsan]
  • A. Eddie Marsan chosen
    Eddie Marsan is a British character actor known for his versatile performances in film and television, including roles in projects like "Ray Donovan," "Happy-Go-Lucky," and numerous Guy Ritchie films.
  • B. Tony Dalton
    Tony Dalton is a Mexican-American actor best known internationally for his roles in the series "Better Call Saul" and Marvel's "Hawkeye."
  • C. Dave Pegg
    Dave Pegg is an English bassist and multi-instrumentalist best known for his long tenure with the folk-rock band Fairport Convention and his work with Jethro Tull.
  • D. James Groves
    James Groves is a person notable enough to be specifically cited as a bearer of the surname Groves.
  • E. Mackenzie Crook
    Mackenzie Crook is an English actor, comedian, writer, and director best known for his roles in "The Office" (UK), the "Pirates of the Caribbean" film series, and the TV series "Detectorists," which he also created.
  • 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_69c008d7a9c4819098d647ec47776917 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0680c02b481908618317566e31a5c completed March 22, 2026, 10:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69c62d73a6ac8190a02602c3506e4226 completed March 27, 2026, 7:10 a.m.
Created at: March 22, 2026, 4:32 p.m.