Triple

T19441746
Position Surface form Disambiguated ID Type / Status
Subject John Cotton E486365 entity
Predicate spouse P13 FINISHED
Object Sarah Hawkred 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: Sarah Hawkred | Statement: [John Cotton, spouse, Sarah Hawkred]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah Hawkred
Context triple: [John Cotton, spouse, Sarah Hawkred]
  • A. Sarah Hawkred chosen
    Sarah Hawkred was the wife of the influential 17th-century Puritan minister and New England clergyman John Cotton.
  • B. Rowena Morrill
    Rowena Morrill was an influential American science fiction and fantasy artist renowned for her vivid, imaginative book and magazine cover illustrations.
  • C. Rowena Cade
    Rowena Cade was a British theatre enthusiast and visionary who designed and built the open-air Minack Theatre into the cliffs of Cornwall largely by hand.
  • D. Rowena Morgan
    Rowena Morgan is a talented young singer and student in the film "Mr. Holland's Opus," whose musical potential deeply inspires her teacher, Glenn Holland.
  • E. Eleanor Gwyn
    Eleanor "Nell" Gwyn was a famed 17th-century English actress and celebrated mistress of King Charles II, renowned for her wit, charm, and rise from humble origins to prominence at court.
  • 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_69d8e8d7ad488190a3373045029b0f3b completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63365343081908683c29f6c4c194b completed April 20, 2026, 2:08 p.m.
Created at: April 10, 2026, 1:38 p.m.