Triple

T19977203
Position Surface form Disambiguated ID Type / Status
Subject John Davidson E493722 entity
Predicate name P16 FINISHED
Object John Davidson — 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: John Davidson | Statement: [John Davidson, name, John Davidson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: John Davidson
Context triple: [John Davidson, name, John Davidson]
  • A. John Davidson
    John Davidson is a former NHL goaltender who became a prominent American hockey broadcaster and television analyst.
  • B. John Davidson
    John Davidson was a Scottish-born botanist and educator who became British Columbia’s first provincial botanist and established the UBC Botanical Garden as a center for plant research and public education.
  • C. John Davidson
    John Davidson was a Scottish poet and playwright of the late 19th century associated with the Decadent and Symbolist movements.
  • D. John Davidson
    John Davidson is an American television personality, actor, and singer best known for hosting popular game shows and variety programs from the 1960s through the 1990s.
  • E. Bill McKinney
    Bill McKinney was an American character actor best known for his intense and often menacing roles in films such as "Deliverance" and numerous Clint Eastwood Westerns.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d1054e08190993b92b86ec5bbc8 completed April 20, 2026, 5:06 p.m.
Created at: April 11, 2026, 3:27 p.m.