Triple

T5317464
Position Surface form Disambiguated ID Type / Status
Subject Peter’s Friends E121585 entity
Predicate director P255 FINISHED
Object Kenneth Branagh E8608 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: Kenneth Branagh | Statement: [Peter’s Friends, director, Kenneth Branagh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kenneth Branagh
Context triple: [Peter’s Friends, director, Kenneth Branagh]
  • A. Kenneth Branagh chosen
    Kenneth Branagh is a Northern Irish actor and filmmaker renowned for his Shakespeare adaptations and acclaimed performances in both stage and screen productions.
  • B. Scott Hicks
    Scott Hicks is an Australian film director best known internationally for his acclaimed 1996 drama "Shine."
  • C. Mark Fiennes
    Mark Fiennes was an English photographer and illustrator, best known as the father of actors Ralph and Joseph Fiennes.
  • D. James Sheridan
    James Sheridan is a British newspaper pioneer credited with founding the influential international business daily, the Financial Times.
  • E. Brian d'Arcy James
    Brian d'Arcy James is an American actor and singer known for his work on Broadway and in film and television, including acclaimed performances in productions like "Shrek the Musical" and the film "Spotlight."
  • 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_69bd463d956c819088105c3db802c017 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd855269ac8190bb7a9248d04f1823 completed March 20, 2026, 5:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf1111f104819094d7646dec32fad2 completed March 21, 2026, 9:43 p.m.
Created at: March 20, 2026, 1:59 p.m.