Triple

T9778054
Position Surface form Disambiguated ID Type / Status
Subject Mr. Holmes E237294 entity
Predicate starring P1507 FINISHED
Object Phil Davis E288079 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: Phil Davis | Statement: [Mr. Holmes, starring, Phil Davis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Phil Davis
Context triple: [Mr. Holmes, starring, Phil Davis]
  • A. Phil Davis
    Phil Davis is a charming, quick-witted song-and-dance man and army veteran who partners with Bob Wallace in the classic musical film "White Christmas."
  • B. Phil Davis chosen
    Phil Davis is an English actor and director known for his character roles in film and television, including prominent work in British crime dramas and literary adaptations.
  • C. Kevin Davis
    Kevin Davis is a Canadian municipal politician who serves as the mayor of Brantford, Ontario.
  • D. Phil Bradley
    Phil Bradley is a former American Major League Baseball outfielder best known for his time with the Seattle Mariners and Philadelphia Phillies in the 1980s.
  • E. Joe Hogue
    Joe Hogue is a music producer known for his work on early recordings by pop artist Katy Perry (then performing as Katy Hudson).
  • 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_69ca84d975a08190aab25b02a89bdab3 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda13545808190a47544b0cc666e20 completed April 1, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1bd22a194819089ae888e932566f1 completed April 5, 2026, 1:38 a.m.
Created at: March 30, 2026, 8:26 p.m.