Triple

T22106955
Position Surface form Disambiguated ID Type / Status
Subject Norman MacCaig E546310 entity
Predicate birthName P65 FINISHED
Object Norman Alexander MacCaig 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: Norman Alexander MacCaig | Statement: [Norman MacCaig, birthName, Norman Alexander MacCaig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Norman Alexander MacCaig
Context triple: [Norman MacCaig, birthName, Norman Alexander MacCaig]
  • A. Norman MacCaig chosen
    Norman MacCaig was a prominent 20th-century Scottish poet renowned for his clear, lyrical verse and vivid depictions of the Scottish landscape and everyday life.
  • B. Gordon Davie
    Gordon Davie is a screenwriter best known for writing the 1998 film "The Interview."
  • C. Ian Macpherson
    Ian Macpherson is a British businessman best known as the founder of the construction and consultancy company Mace Group.
  • D. Ian Macfarlan
    Ian Macfarlan was an Australian politician who briefly served as Premier of Victoria in the 1930s.
  • E. William Gordon MacRae
    William Gordon MacRae is one of the children of British-born American actress and singer Sheila MacRae.
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12919dd388190b8ca08e2464cb0b8 completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.