Triple

T5175370
Position Surface form Disambiguated ID Type / Status
Subject Maud Adams E116783 entity
Predicate workedWith P398 FINISHED
Object John Glen E403804 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: John Glen | Statement: [Maud Adams, workedWith, John Glen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Glen
Context triple: [Maud Adams, workedWith, John Glen]
  • A. John Glen chosen
    John Glen is a British film director best known for directing five James Bond movies during the 1980s.
  • B. John Glynn
    John Glynn was an 18th-century English lawyer and politician whose prominence led to Glynn County in Georgia being named in his honor.
  • C. John Bragg
    John Bragg was a prominent 19th-century figure from Mobile, Alabama, for whom the historic Bragg-Mitchell Mansion is named.
  • D. Gerald Wilkinson
    Gerald Wilkinson was a British naturalist, illustrator, and author known for his influential books on trees, woodlands, and the English countryside.
  • E. Gordon McIlwham
    Gordon McIlwham is a former Scottish rugby union player, best known for his role as a prop and for representing Scotland at international level.
  • 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_69bd446140f08190becb93c61158f27f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7971284481909e6d07b2368a4f76 completed March 20, 2026, 4:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf3a86d58481909752c09fb9fec74e completed March 22, 2026, 12:40 a.m.
Created at: March 20, 2026, 1:45 p.m.