Triple

T15647390
Position Surface form Disambiguated ID Type / Status
Subject Keith Andes E376216 entity
Predicate name P16 FINISHED
Object Keith Andes E376216 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: Keith Andes | Statement: [Keith Andes, name, Keith Andes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keith Andes
Context triple: [Keith Andes, name, Keith Andes]
  • A. Keith Andes chosen
    Keith Andes was an American actor known for his work in mid-20th-century film, television, and theater, including notable roles in productions like "A Date with Judy" and "This Man Is Mine."
  • B. Michael Andrews
    Michael Andrews is an American film composer and musician known for his atmospheric scores for movies such as Donnie Darko and Bridesmaids.
  • C. Michael Andrews
    Michael Andrews was a prominent British painter associated with the School of London, known for his psychologically charged figurative works and atmospheric landscapes.
  • D. Michael Andrews
    Michael Andrews is a film editor best known for his work on major animated features, including the comedy sequel "Shrek the Third."
  • E. Matthew Anden
    Matthew Anden was a German-born American actor known for his work in film and theater, including a role in the psychological drama "David and Lisa."
  • 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_69d85cd1564c8190991adda63bfab4b0 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ed5b8b081908d7127964eed3b09 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff82e921e48190b5b5f4006ad65844 completed May 9, 2026, 6:54 p.m.
Created at: April 10, 2026, 4:15 a.m.