Triple

T22001113
Position Surface form Disambiguated ID Type / Status
Subject David Johnston E543327 entity
Predicate name P16 FINISHED
Object David Lloyd Johnston 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: David Lloyd Johnston | Statement: [David Johnston, name, David Lloyd Johnston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Lloyd Johnston
Context triple: [David Johnston, name, David Lloyd Johnston]
  • A. David Johnston chosen
    David Johnston is a Canadian academic, author, and lawyer who served as the 28th Governor General of Canada from 2010 to 2017.
  • B. David Johnston
    David Johnston is a software developer and entrepreneur best known as a co-founder of Syntrillium Software, the company behind the popular audio editing program Cool Edit.
  • C. Arthur George Brown
    Arthur George Brown was the son of pioneering British aviator Arthur Whitten Brown, who co-piloted the first non-stop transatlantic flight in 1919.
  • D. George Milne
    George Milne was a British Army general who commanded Allied forces on the Macedonian front during World War I.
  • E. Lionel McKenzie
    Lionel McKenzie was an American economist and mathematical theorist known for his foundational contributions to general equilibrium theory and welfare economics.
  • 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_69e11e2c814c8190837d072789000486 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1276ae4e0819097bf1b978451f776 completed April 28, 2026, 9:32 p.m.
Created at: April 16, 2026, 8:20 p.m.