Triple

T16976128
Position Surface form Disambiguated ID Type / Status
Subject John Howard Davies E411814 entity
Predicate name P16 FINISHED
Object John Howard Davies E411814 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: John Howard Davies | Statement: [John Howard Davies, name, John Howard Davies]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Howard Davies
Context triple: [John Howard Davies, name, John Howard Davies]
  • A. John Howard Davies chosen
    John Howard Davies was a British television producer and director, and former child actor, known for his influential work on classic BBC comedies including Monty Python’s Flying Circus and Fawlty Towers.
  • B. Alan Leech
    Alan Leech is an Irish actor best known for his role as Tom Branson in the television series "Downton Abbey."
  • C. Peter Davies
    Peter Davies is a film editor best known for his work on the James Bond movie "A View to a Kill."
  • D. Peter Davies
    Peter Davies was a British publishing house known for issuing notable literary works, including mid-20th-century fiction and historical novels.
  • E. David Lord
    David Lord is a music producer best known for his work on Peter Gabriel’s song "Shock the Monkey."
  • 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_69d886ca8f348190812768ea8d5055ce completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d183ff648190a3cb47242bf7e6ba completed April 18, 2026, 6:46 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00d4755ffc8190a5c861462e33d526 completed May 10, 2026, 6:54 p.m.
Created at: April 10, 2026, 5:32 a.m.