Triple

T6093163
Position Surface form Disambiguated ID Type / Status
Subject Cecilia E135814 entity
Predicate relatedName P3889 FINISHED
Object Cecily E452038 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: Cecily | Statement: [Cecilia, relatedName, Cecily]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cecily
Context triple: [Cecilia, relatedName, Cecily]
  • A. Cecily Harriet d'Autremont
    Cecily Harriet d'Autremont was the wife of longtime CIA counterintelligence chief James Jesus Angleton and a figure in Washington’s mid-20th-century intelligence social circles.
  • B. Gwendolen
    Gwendolen is the given name of Gwen Raverat, a notable British wood engraver and granddaughter of Charles Darwin.
  • C. Cecily More chosen
    Cecily More was one of the daughters of Sir Thomas More, known primarily through her connection to his prominent humanist and political legacy in Tudor England.
  • D. Lady Cecilia Underwood
    Lady Cecilia Underwood was a British noblewoman best known as the second wife of Prince Augustus Frederick, Duke of Sussex, a son of King George III.
  • E. Mary Beaumont
    Mary Beaumont was an English noblewoman of the early 17th century best known as the mother of George Villiers, 1st Duke of Buckingham, a powerful favorite of King James I.
  • 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_69c0087cd3c48190b459848c72d84eb1 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c057ac8c7481909fb22cf157be45ce completed March 22, 2026, 8:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69c125365a7481909e40d01c2d3590aa completed March 23, 2026, 11:34 a.m.
Created at: March 22, 2026, 4:12 p.m.