Triple

T10851561
Position Surface form Disambiguated ID Type / Status
Subject My Father E256157 entity
Predicate author P4 FINISHED
Object Margery Durant E51175 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: Margery Durant | Statement: [My Father, author, Margery Durant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Margery Durant
Context triple: [My Father, author, Margery Durant]
  • A. Margery Durant chosen
    Margery Durant was an American author and socialite best known for her memoir about her father, General Motors founder William C. Durant, and for her involvement in early 20th-century automotive and aviation culture.
  • B. Margery Spencer
    Margery Spencer was the wife of British politician Hamar Greenwood, 1st Viscount Greenwood, who served as Chief Secretary for Ireland during the Irish War of Independence.
  • C. Margery
    Margery is a feminine given name of English origin that has been used since the Middle Ages.
  • D. Margery Seymour
    Margery Seymour was a member of the prominent Seymour family of Tudor England, related to the courtly circle that produced Jane Seymour, third wife of King Henry VIII.
  • E. Margery Corbett Ashby
    Margery Corbett Ashby was a prominent British suffragist, feminist, and international women’s rights leader active in the early to mid-20th century.
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d75117b76c8190b0fb216b1428c3c7 completed April 9, 2026, 7:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb17d978c8190883b4a56e88859de completed April 14, 2026, 9:28 p.m.
Created at: April 8, 2026, 9:20 p.m.