Triple

T895578
Position Surface form Disambiguated ID Type / Status
Subject Mary Easty E19336 entity
Predicate sibling P363 FINISHED
Object Sarah Cloyce E33874 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: Sarah Cloyce | Statement: [Mary Easty, sibling, Sarah Cloyce]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah Cloyce
Context triple: [Mary Easty, sibling, Sarah Cloyce]
  • A. Sarah Cloyce chosen
    Sarah Cloyce was a woman accused during the Salem witch trials, known for being the sister of fellow accused Rebecca Nurse and for later helping to challenge the legitimacy of the proceedings.
  • B. Mary Carr
    Mary Carr was an American character actress of the silent and early sound film era, often cast as kindly maternal figures.
  • C. Faith Coghill
    Faith Coghill was the wife of the renowned English architect Sir Christopher Wren.
  • D. Katherine Clifton
    Katherine Clifton is a central character in Michael Ondaatje's novel "The English Patient," known for her tragic love affair and its far-reaching consequences during World War II.
  • E. Maggie Weston
    Maggie Weston is a British makeup artist and costume designer best known for her long-term collaboration with filmmaker Terry Gilliam on several of his visually distinctive films.
  • 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_69a4939d37188190848be3d426ebc9ae completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ad23d6e88190a2fb5e1e168a7b44 completed March 1, 2026, 9:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69adf3a24d9c8190926a3946a89105e1 completed March 8, 2026, 10:09 p.m.
Created at: March 1, 2026, 7:39 p.m.