Triple

T18586303
Position Surface form Disambiguated ID Type / Status
Subject John Burnside E454243 entity
Predicate name P16 FINISHED
Object John Burnside 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: John Burnside | Statement: [John Burnside, name, John Burnside]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Burnside
Context triple: [John Burnside, name, John Burnside]
  • A. John Burnside chosen
    John Burnside is a Scottish poet, novelist, and essayist known for his lyrical explorations of nature, memory, and the uncanny in contemporary literature.
  • B. Richard Siken
    Richard Siken is an American poet best known for his intense, cinematic collection "Crush," which brought him widespread acclaim in contemporary poetry.
  • C. Kay Young
    Kay Young was a British actress known for her stage and film work in the mid-20th century.
  • D. Franz Wright
    Franz Wright was a Pulitzer Prize–winning American poet known for his intensely personal, spiritually searching verse and for being the son of fellow poet James Wright.
  • E. Paul Doty
    Paul Doty was an American chemist and prominent arms control expert who played a key role in nuclear disarmament policy and science advising during the Cold War.
  • 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_69d8d38ae7e081908a98df1251842402 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e545b210488190ba62d3bf6e1a595c completed April 19, 2026, 9:14 p.m.
Created at: April 10, 2026, 11:44 a.m.