Triple

T17411633
Position Surface form Disambiguated ID Type / Status
Subject Stedman Graham E423378 entity
Predicate child P120 FINISHED
Object Wendy Graham 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: Wendy Graham | Statement: [Stedman Graham, child, Wendy Graham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wendy Graham
Context triple: [Stedman Graham, child, Wendy Graham]
  • A. Wendy Graham chosen
    Wendy Graham is the daughter of American educator, author, and businessman Stedman Graham.
  • B. Mary Wakefield
    Mary Wakefield is a British journalist and magazine editor best known for her work at The Spectator and her marriage to political strategist Dominic Cummings.
  • C. Wendy Hughes
    Wendy Hughes was an acclaimed Australian actress known for her versatile performances in film, television, and theatre from the 1970s onward.
  • D. Mary Cox
    Mary Cox is best known as the longtime wife of American actor and musician Ronny Cox.
  • E. Mary Cox
    Mary Cox is a central character in the British television drama "Our Friends in the North," whose life and relationships reflect the social and political changes in late 20th-century Britain.
  • 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_69d889d7d27c819088486ce3f0627fa1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43b0b56788190ba012788f32afb78 completed April 19, 2026, 2:16 a.m.
Created at: April 10, 2026, 5:46 a.m.