Triple

T13342482
Position Surface form Disambiguated ID Type / Status
Subject Frances Macdonald E317859 entity
Predicate familyName P18 FINISHED
Object Macdonald E301571 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: Macdonald | Statement: [Frances Macdonald, familyName, Macdonald]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Macdonald
Context triple: [Frances Macdonald, familyName, Macdonald]
  • A. Maclean
    Maclean is a riverside town in northern New South Wales, Australia, known for its strong Scottish heritage and annual Highland Gathering.
  • B. MacDonald chosen
    MacDonald is a common Scottish surname historically associated with the powerful Clan Donald and borne by numerous notable figures in politics, arts, and public life.
  • C. William Christopher Macdonald
    William Christopher Macdonald was a Canadian tobacco manufacturer and philanthropist best known for his major endowments to education, including funding institutions such as the Macdonald Institute.
  • D. John MacDonald
    John MacDonald is a business founder and entrepreneur best known for establishing the company MDA.
  • E. John Mackenzie
    John Mackenzie was a Scottish film and television director best known for his gritty British crime drama "The Long Good Friday" (1980).
  • 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_69d806b5a3c08190b42c267fb092f98a completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d99d0379d481909a50fff31b19fed1 completed April 11, 2026, 12:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69f71f417e4081908ab2025a313bfad1 completed May 3, 2026, 10:11 a.m.
Created at: April 9, 2026, 9:31 p.m.