Triple

T19107521
Position Surface form Disambiguated ID Type / Status
Subject Ethel Snowden E467694 entity
Predicate spouse P13 FINISHED
Object Philip Snowden 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: Philip Snowden | Statement: [Ethel Snowden, spouse, Philip Snowden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Philip Snowden
Context triple: [Ethel Snowden, spouse, Philip Snowden]
  • A. Philip Snowden chosen
    Philip Snowden was a British Labour politician and economist who became the first Labour Chancellor of the Exchequer, known for his strict adherence to fiscal orthodoxy during the interwar period.
  • B. Ronald Oxburgh
    Ronald Oxburgh is a British geologist and crossbench life peer known for his contributions to earth sciences and his leadership roles in academia, government, and the energy sector.
  • C. Christopher Woodward
    Christopher Woodward is an architect known for his role in designing the Centre:MK shopping and leisure complex in Milton Keynes, England.
  • D. Boris Hauntley
    Boris Hauntley is a character from the children's animated series "Vampirina," known as Vampirina's supportive vampire father.
  • E. Martin Wood
    Martin Wood is a Canadian television director best known for his extensive work on science fiction series such as Stargate SG-1, Stargate Atlantis, and Sanctuary.
  • 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e391245c8190b1393577b61c4f76 completed April 20, 2026, 8:28 a.m.
Created at: April 10, 2026, 12:04 p.m.