Triple

T5518516
Position Surface form Disambiguated ID Type / Status
Subject Jeremy Potts E144745 entity
Predicate hasRelative P367 FINISHED
Object Jemima Potts E103377 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: Jemima Potts | Statement: [Jeremy Potts, hasRelative, Jemima Potts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jemima Potts
Context triple: [Jeremy Potts, hasRelative, Jemima Potts]
  • A. Jemima Potts chosen
    Jemima Potts is one of the adventurous children in the classic family story "Chitty Chitty Bang Bang," known for her role in the magical car’s whimsical journeys.
  • B. Pippa Harris
    Pippa Harris is a British film and television producer, co-founder of Neal Street Productions, known for her collaborations with Sam Mendes on projects such as the World War I film "1917."
  • C. Linda Partridge
    Linda Partridge is a British geneticist and biogerontologist renowned for her pioneering research on the biology of ageing and age-related diseases.
  • D. Kasidy Yates
    Kasidy Yates is a civilian freighter captain and the romantic partner of Captain Benjamin Sisko in the television series Star Trek: Deep Space Nine.
  • E. Lisa Howard
    Lisa Howard was an American actress active in the mid-20th century, known for her work in film, television, and theater.
  • 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_69c008f77ff88190b0cd50ca207295d1 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01f6cefe48190bfda90d6afab8468 completed March 22, 2026, 4:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69c027e1ed4c81908f670286556ced81 completed March 22, 2026, 5:33 p.m.
Created at: March 22, 2026, 3:33 p.m.