Triple

T10937777
Position Surface form Disambiguated ID Type / Status
Subject Tommy Shelby E258381 entity
Predicate creator P184 FINISHED
Object Steven Knight E183571 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: Steven Knight | Statement: [Tommy Shelby, creator, Steven Knight]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steven Knight
Context triple: [Tommy Shelby, creator, Steven Knight]
  • A. Steven Knight chosen
    Steven Knight is a British screenwriter, director, and producer best known for creating the television series "Peaky Blinders" and writing acclaimed films such as "Dirty Pretty Things" and "Eastern Promises."
  • B. Sam Winder
    Sam Winder is a person notable enough to be specifically recorded as a bearer of the surname Winder.
  • C. Nic Pizzolatto
    Nic Pizzolatto is an American writer and producer best known for creating and writing the critically acclaimed HBO crime anthology series True Detective.
  • D. Michael Caton-Jones
    Michael Caton-Jones is a Scottish film director known for works such as "Scandal," "Rob Roy," and "The Jackal."
  • E. Alan Ball
    Alan Ball is an American screenwriter, director, and producer best known for creating the television series "Six Feet Under" and "True Blood" and for writing the Oscar-winning film "American Beauty."
  • 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_69d6aa8769b4819082bfe5e61b9017f0 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d770b065288190b4216beee8e8a193 completed April 9, 2026, 9:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69e23bfd6a108190a0557598f68659fa completed April 17, 2026, 1:56 p.m.
Created at: April 8, 2026, 9:23 p.m.