Triple

T16952059
Position Surface form Disambiguated ID Type / Status
Subject MacDermott E411204 entity
Predicate hasNotableBearer P458 FINISHED
Object Hugh MacDermott 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: Hugh MacDermott | Statement: [MacDermott, hasNotableBearer, Hugh MacDermott]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hugh MacDermott
Context triple: [MacDermott, hasNotableBearer, Hugh MacDermott]
  • A. Hugh McDermott chosen
    Hugh McDermott was a Scottish actor known for his supporting roles in British films of the 1930s and 1940s.
  • B. Stephen McDermott
    Stephen McDermott is an Irish Gaelic footballer known for playing at inter-county level for Donegal.
  • C. Gerald MacDermott
    Gerald McDermott was an American author and illustrator best known for his vibrant, Caldecott Medal–winning picture books based on world folktales and myths.
  • D. Brian McDermott
    Brian McDermott is a former professional rugby league player and highly successful English rugby league coach, best known for his trophy-laden tenure with the Leeds Rhinos.
  • E. Patrick S. Dinneen
    Patrick S. Dinneen was an Irish lexicographer and scholar best known for his influential Irish-English dictionary and contributions to the revival of the Irish language.
  • 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_69d886c9c9d481909afe222093641cae completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d0197f308190af7185fc9cc7a6e9 completed April 18, 2026, 6:40 p.m.
Created at: April 10, 2026, 5:31 a.m.