Triple

T22765910
Position Surface form Disambiguated ID Type / Status
Subject Sarah Horton E563123 entity
Predicate spouse P13 FINISHED
Object Roger Conant 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: Roger Conant | Statement: [Sarah Horton, spouse, Roger Conant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roger Conant
Context triple: [Sarah Horton, spouse, Roger Conant]
  • A. Roger Conant chosen
    Roger Conant was an early English colonist and leader best known for establishing the settlement that became Salem, Massachusetts in the 17th century.
  • B. Dave Driscoll
    Dave Driscoll is a private individual known primarily for being a relative of Levi Sanders, the son of U.S. Senator Bernie Sanders.
  • C. Michael Atkinson
    Michael Atkinson is a name shared by several notable individuals, including politicians, writers, and public figures in English-speaking countries.
  • D. Terry Cafolla
    Terry Cafolla is a Northern Irish screenwriter and playwright known for his work on television dramas and films.
  • E. Michael Gunton
    Michael Gunton is a British television producer best known for his work on major BBC natural history series such as Planet Earth II and Dynasties.
  • 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_69e24552e11c81909c2d61578a558bd7 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17a80249c819091569e7b8d500b45 completed April 29, 2026, 3:26 a.m.
Created at: April 17, 2026, 3:26 p.m.