Triple

T19893818
Position Surface form Disambiguated ID Type / Status
Subject Elizabeth Jane Howard E478097 entity
Predicate spouse P13 FINISHED
Object Peter Scott E110332 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: Peter Scott | Statement: [Elizabeth Jane Howard, spouse, Peter Scott]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Scott
Context triple: [Elizabeth Jane Howard, spouse, Peter Scott]
  • A. Peter Scott chosen
    Peter Scott was a British conservationist, ornithologist, and painter who played a key role in global wildlife preservation efforts and co-founded the World Wildlife Fund.
  • B. David Shepherd
    David Shepherd is the fictional protagonist of the 2009 television series "Kings," a modern reimagining of the biblical David who rises from humble soldier to political and spiritual leader in a contemporary monarchy.
  • C. Paul Broughton
    Paul Broughton is an actor best known for his role in the British television drama series "The Lakes."
  • D. Nigel Lindsay
    Nigel Lindsay is a British actor known for his work on stage and screen, including originating the title role in the West End production of Shrek the Musical.
  • 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 (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_69d8e51f32b08190b3687f4f60353250 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e659105d7481909131d9907ac0094b completed April 20, 2026, 4:49 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07f6d9dff881909ef10d970af692ba completed May 16, 2026, 4:47 a.m.
Created at: April 10, 2026, 1:52 p.m.