Triple

T19663906
Position Surface form Disambiguated ID Type / Status
Subject S. (novel) E472151 entity
Predicate hasTitleCharacter P5716 FINISHED
Object Sarah Worth 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 Worth | Statement: [S. (novel), hasTitleCharacter, Sarah Worth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah Worth
Context triple: [S. (novel), hasTitleCharacter, Sarah Worth]
  • A. Sarah Worth chosen
    Sarah Worth is the protagonist of the satirical novel "S." by John Updike, around whom the story’s exploration of self-discovery and spiritual seeking revolves.
  • B. Sarah Hoadly
    Sarah Hoadly was an English portrait painter of the early 18th century, known for her refined style and connections to prominent artistic circles in London.
  • C. Sarah Trowbridge Ward
    Sarah Trowbridge Ward was the wife of American Revolutionary War general and early Continental Army commander Artemas Ward.
  • D. Charlotte Leslie
    Charlotte Leslie is a British Conservative politician who served as the Member of Parliament for Bristol North West from 2010 to 2017.
  • E. Sarah Wharton
    Sarah Wharton is the sister of Frances Wharton, about whom little else is publicly documented.
  • 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_69d8e514f2e08190ba70a4449519d218 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6416671fc81908e25b0477234fa0f completed April 20, 2026, 3:08 p.m.
Created at: April 10, 2026, 1:45 p.m.