Triple

T15576516
Position Surface form Disambiguated ID Type / Status
Subject For Queen and Country E374382 entity
Predicate starring P1507 FINISHED
Object Frank Windsor E509905 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: Frank Windsor | Statement: [For Queen and Country, starring, Frank Windsor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Windsor
Context triple: [For Queen and Country, starring, Frank Windsor]
  • A. Frank Windsor chosen
    Frank Windsor was a British character actor best known for his television work, particularly in police dramas such as "Z-Cars" and its spin-offs.
  • B. Albert Windsor
    Albert Windsor is a young member of the extended British royal family and the son of Lord Nicholas Windsor.
  • C. William of Windsor
    William of Windsor was a short-lived English prince of the 14th century, the youngest son of King Edward III and Philippa of Hainault.
  • D. Thomas of Windsor
    Thomas of Windsor was an English royal of the 14th century, a younger son of King Edward III and Queen Philippa of Hainault.
  • E. Alexander Windsor, Earl of Ulster
    Alexander Windsor, Earl of Ulster, is a member of the British royal family and the only son of Prince Richard, Duke of Gloucester, and Birgitte, Duchess of Gloucester.
  • 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_69d85ccd575081908909b71a3f3e3a61 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e22c89081909b1ec0cd36a1ef45 completed April 16, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c4978ec8190a57de5d9a2ec6653 completed May 9, 2026, 3:01 p.m.
Created at: April 10, 2026, 4:10 a.m.