Triple

T19697888
Position Surface form Disambiguated ID Type / Status
Subject Susanna Shakespeare E473010 entity
Predicate child P120 FINISHED
Object Elizabeth Barnard 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: Elizabeth Barnard | Statement: [Susanna Shakespeare, child, Elizabeth Barnard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth Barnard
Context triple: [Susanna Shakespeare, child, Elizabeth Barnard]
  • A. Elizabeth Barnard
    Elizabeth Barnard was an English gentlewoman of the late 17th and early 18th centuries, best known as the mother of James Brydges, who became the 1st Duke of Chandos.
  • B. Elizabeth Barnard chosen
    Elizabeth Barnard was the granddaughter of William Shakespeare and his last surviving direct descendant, known for leaving no heirs and thus ending Shakespeare’s bloodline.
  • C. Anne Barnard
    Anne Barnard is a journalist and foreign correspondent known for her reporting on conflict zones and Middle Eastern affairs, particularly for The New York Times.
  • D. Elizabeth Denniston
    Elizabeth Denniston was the wife of Irish-born American surveyor and Revolutionary War officer Charles Clinton.
  • E. Sarah Barnard
    Sarah Barnard is a relatively obscure individual for whom no widely known public information or distinguishing background is readily available.
  • 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_69d8e515bef88190bc30781aea50537a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e642b2baec81909ee2cd6ead632836 completed April 20, 2026, 3:13 p.m.
Created at: April 10, 2026, 1:46 p.m.