Triple

T20610176
Position Surface form Disambiguated ID Type / Status
Subject Angela Thorne E506426 entity
Predicate spouse P13 FINISHED
Object Peter Penry-Jones 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: Peter Penry-Jones | Statement: [Angela Thorne, spouse, Peter Penry-Jones]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Penry-Jones
Context triple: [Angela Thorne, spouse, Peter Penry-Jones]
  • A. Peter Penry-Jones chosen
    Peter Penry-Jones was a Welsh actor known for his work in British television and theatre and as the father of actor Rupert Penry-Jones.
  • B. Pete Glenister
    Pete Glenister is a British songwriter, guitarist, and producer known for his work with artists such as Alison Moyet and Kirsty MacColl.
  • C. Laurence Fox
    Laurence Fox is an English actor and political activist known for his role in the TV series "Lewis" and for his outspoken, often controversial public commentary.
  • D. Jonathan Gullis
    Jonathan Gullis is a British Conservative Party politician who has served as the Member of Parliament for Stoke-on-Trent North since 2019.
  • E. Michael Jayston
    Michael Jayston is an English actor known for his work in television, film, and theatre, including prominent roles in classic British dramas and genre series.
  • 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_69e0b4bb2b4081908fa4a72444120f35 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aad6f53481908fb242947dda7028 completed April 20, 2026, 10:38 p.m.
Created at: April 16, 2026, 11:41 a.m.