Triple

T22798095
Position Surface form Disambiguated ID Type / Status
Subject Luke Mitchell E564303 entity
Predicate notableWork P4 FINISHED
Object Tom Swift 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: Tom Swift | Statement: [Luke Mitchell, notableWork, Tom Swift]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Swift
Context triple: [Luke Mitchell, notableWork, Tom Swift]
  • A. Tom Swift chosen
    Tom Swift is the adventurous teenage inventor and protagonist of a long-running series of American science fiction and adventure novels for young readers.
  • B. Joe Swift
    Joe Swift is a British garden designer, television presenter, and writer best known for his work on the BBC gardening show "Gardeners' World."
  • C. Freddie Bobbsey
    Freddie Bobbsey is one of the young twin siblings in the classic children's mystery and adventure book series "The Bobbsey Twins."
  • D. Lewis Swift
    Lewis Swift was a 19th-century American astronomer known for his discovery of numerous comets and deep-sky objects.
  • E. Bert Bobbsey
    Bert Bobbsey is one of the twin brothers in the classic children's book series "The Bobbsey Twins," known for his adventurous and energetic personality.
  • 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_69e2458185f88190b0045227ee420411 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17cda76448190891c5190e1d75ae0 completed April 29, 2026, 3:36 a.m.
Created at: April 17, 2026, 3:30 p.m.