Triple

T14592857
Position Surface form Disambiguated ID Type / Status
Subject Back Award E342486 entity
Predicate hasRecipient P108 FINISHED
Object Michael Batty E1108938 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: Michael Batty | Statement: [Back Award, hasRecipient, Michael Batty]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Batty
Context triple: [Back Award, hasRecipient, Michael Batty]
  • A. Professor Michael Batty chosen
    Professor Michael Batty is a prominent urban planning and spatial analysis scholar known for pioneering work in urban modeling and the application of complexity theory to cities.
  • B. Frederick Goodchild
    Frederick Goodchild was a Canadian publisher best known as a co-founder of the influential Canadian publishing house McClelland and Stewart.
  • C. Christopher Dorling
    Christopher Dorling is a British publisher best known as the co-founder of the illustrated reference book publisher Dorling Kindersley (DK).
  • D. Laurence Keen
    Laurence Keen is a British professional golfer known for competing on developmental tours and national circuits.
  • E. David Harvey
    David Harvey is a prominent Marxist geographer and social theorist known for his influential critiques of capitalism and urbanization.
  • 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_69d822ddc0f081909cd8163c7de298cd completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb43480d8819084a707e56da2c237 completed April 14, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdd5c79c488190a134d2b0435e899e completed May 8, 2026, 12:23 p.m.
Created at: April 10, 2026, 1:24 a.m.