Triple

T3129845
Position Surface form Disambiguated ID Type / Status
Subject Coffee and Cigarettes E65382 entity
Predicate stars P1956 FINISHED
Object Steve Coogan E69082 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: Steve Coogan | Statement: [Coffee and Cigarettes, stars, Steve Coogan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steve Coogan
Context triple: [Coffee and Cigarettes, stars, Steve Coogan]
  • A. Steve Coogan chosen
    Steve Coogan is an English actor, comedian, writer, and producer known for his character Alan Partridge and a wide range of film and television roles.
  • B. Rob Brydon
    Rob Brydon is a Welsh actor, comedian, impressionist, and presenter best known for his work on British television series such as "Gavin & Stacey" and "The Trip."
  • C. Ian Hart
    Ian Hart is an English actor known for his versatile character roles in film and television, including his portrayal of Professor Quirrell in "Harry Potter and the Philosopher's Stone."
  • D. Jack Whitehall
    Jack Whitehall is a British comedian, actor, and writer known for his stand-up comedy and roles in series like "Fresh Meat" and "Bad Education," as well as various film and presenting work.
  • E. Chris O'Dowd
    Chris O'Dowd is an Irish actor and comedian best known for his roles in the sitcom "The IT Crowd" and various film comedies.
  • 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_69ad8580c72481909672d37acf647893 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada549aaa881908dcf92d20fa6f238 completed March 8, 2026, 4:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69b20f7f9e288190af5f2b2aa6ff63b3 completed March 12, 2026, 12:57 a.m.
Created at: March 8, 2026, 3:04 p.m.