Triple

T5317182
Position Surface form Disambiguated ID Type / Status
Subject Philip Larkin E121580 entity
Predicate familyName P18 FINISHED
Object Larkin E121580 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: Larkin | Statement: [Philip Larkin, familyName, Larkin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Larkin
Context triple: [Philip Larkin, familyName, Larkin]
  • A. Philip Larkin chosen
    Philip Larkin was a 20th-century English poet and librarian renowned for his bleakly lyrical, accessible verse that captured postwar British life with wit, precision, and emotional restraint.
  • B. Douglas Dunn
    Douglas Dunn is a Scottish poet, editor, and academic known for his reflective verse and significant contributions to contemporary British poetry.
  • C. William Davies
    William Davies is a British screenwriter known for his work on popular films such as the "How to Train Your Dragon" series and "Johnny English."
  • D. Edward Bishop
    Edward Bishop was a 17th-century New England resident known primarily as the husband of Bridget Bishop, the first person executed during the Salem witch trials.
  • E. David Harsent
    David Harsent is a British poet and librettist known for his dark, formally inventive work and multiple major poetry awards.
  • 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_69bd463d956c819088105c3db802c017 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd854fd07c8190b4f1c3c8e618c308 completed March 20, 2026, 5:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf1111f104819094d7646dec32fad2 completed March 21, 2026, 9:43 p.m.
Created at: March 20, 2026, 1:59 p.m.