Triple

T19367791
Position Surface form Disambiguated ID Type / Status
Subject William Dyce E484447 entity
Predicate name P16 FINISHED
Object William Dyce 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: William Dyce | Statement: [William Dyce, name, William Dyce]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Dyce
Context triple: [William Dyce, name, William Dyce]
  • A. William Dyce chosen
    William Dyce was a 19th-century Scottish painter and influential art educator associated with the early Pre-Raphaelite movement.
  • B. Frederic Leighton
    Frederic Leighton was a prominent 19th-century British painter and sculptor associated with the Victorian neoclassical movement and known for his richly colored, idealized historical and mythological works.
  • C. George Leighton
    George Leighton is a name shared by several notable figures, including artists, writers, and public officials, whose specific identity depends on the historical and professional context.
  • D. George Richmond
    George Richmond is a British cinematographer known for his dynamic visual work on action films such as "Kingsman: The Secret Service."
  • E. Daniel Maclise
    Daniel Maclise was a 19th-century Irish-born painter renowned for his large-scale historical and literary scenes, particularly in Victorian 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_69d8e8d305088190ad13571532aa454c completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e619adac8881909136c50351f3683d completed April 20, 2026, 12:18 p.m.
Created at: April 10, 2026, 1:35 p.m.