Triple

T18611320
Position Surface form Disambiguated ID Type / Status
Subject David Harsent E454900 entity
Predicate name P16 FINISHED
Object David Harsent 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: David Harsent | Statement: [David Harsent, name, David Harsent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Harsent
Context triple: [David Harsent, name, David Harsent]
  • A. David Harsent chosen
    David Harsent is a British poet and librettist known for his dark, formally inventive work and multiple major poetry awards.
  • B. John Kinsella
    John Kinsella is an American swimmer and Olympic medalist known for his achievements in freestyle events during the late 1960s and early 1970s.
  • C. Douglas Dunn
    Douglas Dunn is a Scottish poet, editor, and academic known for his reflective verse and significant contributions to contemporary British poetry.
  • D. George Szirtes
    George Szirtes is a Hungarian-born British poet, translator, and editor renowned for his lyrical verse and influential translations of Hungarian literature into English.
  • E. Craig Raine
    Craig Raine is a British poet and critic best known as a leading figure of the 1970s–80s "Martian" school of poetry, noted for its startling, estranging metaphors and imaginative re-descriptions of everyday life.
  • 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_69d8d38bbe7c8190bdec3138e7d413c9 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e54d013748819099126e27e7ec543d completed April 19, 2026, 9:45 p.m.
Created at: April 10, 2026, 11:45 a.m.