Triple

T15535682
Position Surface form Disambiguated ID Type / Status
Subject Joe Cornish E370332 entity
Predicate collaboratedWith P435 FINISHED
Object Adam Buxton E794255 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: Adam Buxton | Statement: [Joe Cornish, collaboratedWith, Adam Buxton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adam Buxton
Context triple: [Joe Cornish, collaboratedWith, Adam Buxton]
  • A. Adam Buxton chosen
    Adam Buxton is a British comedian, writer, actor, and podcaster best known as one half of the comedy duo Adam and Joe and for hosting "The Adam Buxton Podcast."
  • B. Chris Britton
    Chris Britton is an English rock guitarist best known as a member of the 1960s garage rock band The Troggs, famed for hits like "Wild Thing."
  • C. Michael Ellis
    Michael Ellis is a screenwriter best known for co-writing the romantic comedy film "The Wedding Planner."
  • D. Michael Ellis
    Michael Ellis is a film editor best known for his work on the British comedy-drama film "Brassed Off."
  • E. Alec Mills
    Alec Mills is a British cinematographer best known for his work on several James Bond films, including serving as director of photography on "License to Kill."
  • 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_69d85cc521a08190921fb50319dddc34 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e0442e327c8190b4b879c8a3cd38e3 completed April 16, 2026, 2:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4556ad008190a411ccd3ef0d1e89 completed May 9, 2026, 2:31 p.m.
Created at: April 10, 2026, 4:06 a.m.