Triple

T19522499
Position Surface form Disambiguated ID Type / Status
Subject John Shore E488434 entity
Predicate name P16 FINISHED
Object John Shore 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 Shore | Statement: [John Shore, name, John Shore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Shore
Context triple: [John Shore, name, John Shore]
  • A. John Shore chosen
    John Shore was a British colonial administrator who served as Governor-General of India and played a key role in shaping late 18th-century revenue and land settlement policies in Bengal.
  • B. Henry Marshal
    Henry Marshal was a medieval English nobleman and clergyman, best known as the Bishop of Exeter in the late 12th and early 13th centuries.
  • C. George Hastings
    George Hastings was an English nobleman of the Hastings family, known as the son and heir of Francis Hastings, 2nd Earl of Huntingdon.
  • D. Sam Leitch
    Sam Leitch was a British sports broadcaster best known for his influential work presenting football coverage on BBC television.
  • E. Robert Cates
    Robert Cates is known primarily as the husband of the late American actress Darlene Cates, who gained recognition for her role in the film "What's Eating Gilbert Grape."
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e635a1ae9881908dfdcc94490c57aa completed April 20, 2026, 2:18 p.m.
Created at: April 10, 2026, 1:40 p.m.