Triple

T23141341
Position Surface form Disambiguated ID Type / Status
Subject Joan Goushill E577468 entity
Predicate child P120 FINISHED
Object John Stanley 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 Stanley | Statement: [Joan Goushill, child, John Stanley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Stanley
Context triple: [Joan Goushill, child, John Stanley]
  • A. John Stanley
    John Stanley is a British Conservative politician who served as a Member of Parliament for several decades and held multiple ministerial roles in defense and foreign affairs.
  • B. John Stanley chosen
    John Stanley was an 18th-century English composer and organist, renowned for his organ voluntaries and other church and instrumental music.
  • C. Bill Morrow
    Bill Morrow was an American television and radio comedy writer best known for his work on major mid-20th-century variety and comedy programs.
  • D. Robert Stein
    Robert Stein is a relatively common personal name shared by multiple individuals across various professions, including academia, business, and the arts.
  • E. Sidney Lippman
    Sidney Lippman was an American songwriter best known for co-writing the popular 1951 hit song "Too Young."
  • 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_69e245f8e6248190ba3d58e068b4dccb completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18eca8a9081908dcc39409f615b7c completed April 29, 2026, 4:53 a.m.
Created at: April 17, 2026, 4 p.m.