Triple

T18919862
Position Surface form Disambiguated ID Type / Status
Subject Davie E462820 entity
Predicate hasSpellingVariant P457 FINISHED
Object Davies 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: Davies | Statement: [Davie, hasSpellingVariant, Davies]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Davies
Context triple: [Davie, hasSpellingVariant, Davies]
  • A. Davies chosen
    Davies is a common Welsh-origin surname borne by numerous notable individuals across fields such as literature, politics, sports, and entertainment.
  • B. Will Davies
    Will Davies is a British screenwriter and film producer known for his work on popular family and animated films, including co-writing the story for "Puss in Boots."
  • C. Mark Davies
    Mark Davies is a scholar and editor known for his work on classic ghost stories, including editing M. R. James’s tale "The Tractate Middoth."
  • D. Michael Davies
    Michael Davies is a British-born television producer best known for creating and producing popular talk and game shows, including work on "Watch What Happens Live with Andy Cohen" and "Who Wants to Be a Millionaire."
  • E. Daniel Davies
    Daniel Davies is a British-American musician and film composer known for his atmospheric, synth-driven scores and frequent collaborations with director John Carpenter.
  • 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_69d8dcfdbbb881909964fa5a75bd0b48 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c62a264c81909f6d5df841486efc completed April 20, 2026, 6:22 a.m.
Created at: April 10, 2026, 11:59 a.m.