Triple

T20384378
Position Surface form Disambiguated ID Type / Status
Subject Mary Hayley Bell E497922 entity
Predicate child P120 FINISHED
Object Jonathan Mills 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: Jonathan Mills | Statement: [Mary Hayley Bell, child, Jonathan Mills]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jonathan Mills
Context triple: [Mary Hayley Bell, child, Jonathan Mills]
  • A. Jonathan Mills chosen
    Jonathan Mills is a member of the British acting family headed by Sir John Mills and the brother of actress Hayley Mills.
  • B. Duncan Mills
    Duncan Mills is a music producer and mixer known for his work with a range of indie and alternative artists.
  • C. Steve Oram
    Steve Oram is a British actor, writer, and comedian known for his work in darkly comic films such as "Sightseers" and various British television series.
  • D. Michael Buckland
    Michael Buckland is an American information scientist and librarian known for his influential work on information retrieval, library services, and the theory of information systems.
  • E. Gordon Mills
    Gordon Mills was a prominent British music manager and record producer best known for shaping the careers of artists like Tom Jones and Engelbert Humperdinck.
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e678b2ceec819091ad5205ee9b2174 completed April 20, 2026, 7:04 p.m.
Created at: April 16, 2026, 11:28 a.m.