Triple

T19971957
Position Surface form Disambiguated ID Type / Status
Subject TT3D: Closer to the Edge E480098 entity
Predicate producer P490 FINISHED
Object Richard De Aragues 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: Richard De Aragues | Statement: [TT3D: Closer to the Edge, producer, Richard De Aragues]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richard De Aragues
Context triple: [TT3D: Closer to the Edge, producer, Richard De Aragues]
  • A. Richard De Aragues chosen
    Richard De Aragues is a British film director best known for his acclaimed motorcycle racing documentary "TT3D: Closer to the Edge."
  • B. Henry Borrell
    Henry Borrell was a clockmaker associated with the timekeeping installations of St. Michael's Church.
  • C. Jean Guiton
    Jean Guiton was a French Huguenot naval leader and mayor of La Rochelle who became a symbol of Protestant resistance during the city’s struggle against royal authority in the early 17th century.
  • D. Roger de La Fresnaye
    Roger de La Fresnaye was a French Cubist painter known for his structured, geometric compositions that bridged traditional representation and modernist abstraction in the early 20th century.
  • E. Peter De Sarigny
    Peter De Sarigny was a film producer known for his work on mid-20th-century British cinema.
  • 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_69d8e523c19881909f9197037200dde6 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65bc9694881909a31841702ab9e5f completed April 20, 2026, 5 p.m.
Created at: April 10, 2026, 1:54 p.m.