Triple

T17546751
Position Surface form Disambiguated ID Type / Status
Subject Colin Blakely E427345 entity
Predicate name P16 FINISHED
Object Colin George Blakely 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: Colin George Blakely | Statement: [Colin Blakely, name, Colin George Blakely]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Colin George Blakely
Context triple: [Colin Blakely, name, Colin George Blakely]
  • A. Colin Blakely chosen
    Colin Blakely was a Northern Irish character actor known for his powerful stage work and memorable supporting roles in British and international films of the 1960s–1980s.
  • B. Brian Paisley
    Brian Paisley is a Canadian theatre producer and writer best known for creating the Edmonton Fringe Theatre Festival, which helped popularize the fringe theatre movement in North America.
  • C. Ben Hayslip
    Ben Hayslip is an American country music songwriter known for penning numerous hit songs for major Nashville artists.
  • D. Kent Rogers
    Kent Rogers was an American voice actor best known for his work in classic Warner Bros. cartoons during the 1940s.
  • E. Jay McGraw
    Jay McGraw is an American television producer, author, and the son of TV personality Dr. Phil McGraw, known for producing and appearing on various reality and talk shows.
  • 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_69d889df6dc081908f67dbadc03c07ee completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e454626cfc8190a2602ba4934b8e6d completed April 19, 2026, 4:04 a.m.
Created at: April 10, 2026, 5:49 a.m.