Triple

T12197515
Position Surface form Disambiguated ID Type / Status
Subject Peter Cook E290624 entity
Predicate spouse P13 FINISHED
Object Wendy Snowden E290624 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: Wendy Snowden | Statement: [Peter Cook, spouse, Wendy Snowden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wendy Snowden
Context triple: [Peter Cook, spouse, Wendy Snowden]
  • A. Wendy Snowden chosen
    Wendy Snowden is best known as the former wife of British satirist and comedian Peter Cook.
  • B. Lindsay Mills Snowden
    Lindsay Mills Snowden is an American acrobat and blogger best known as the longtime partner of NSA whistleblower Edward Snowden.
  • C. Ethel Snowden
    Ethel Snowden was a prominent British socialist, feminist, and pacifist activist in the early 20th century, known for her work in the Labour movement and campaigns for women's rights.
  • D. Stella Assange
    Stella Assange is a human rights lawyer and activist best known for her work defending WikiLeaks founder Julian Assange and campaigning against his extradition.
  • E. Chelsea Manning
    Chelsea Manning is a former U.S. Army intelligence analyst and whistleblower who leaked classified documents to WikiLeaks, sparking global debates on government transparency, surveillance, and war.
  • 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_69d6ab64de5881908d56eb7a75c6cc69 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91c56b4d88190b6a32baff3375dc4 completed April 10, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60a9150448190b30e6e2dd8eec3b4 completed May 2, 2026, 2:30 p.m.
Created at: April 8, 2026, 9:50 p.m.