Triple

T14805437
Position Surface form Disambiguated ID Type / Status
Subject Line of Duty E348021 entity
Predicate director P255 FINISHED
Object Jed Mercurio E955901 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: Jed Mercurio | Statement: [Line of Duty, director, Jed Mercurio]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jed Mercurio
Context triple: [Line of Duty, director, Jed Mercurio]
  • A. Jed Mercurio chosen
    Jed Mercurio is a British television writer, producer, and former physician best known for creating acclaimed drama series such as Line of Duty and Bodyguard.
  • B. Neil Clarke
    Neil Clarke is an influential science fiction editor and publisher, best known as the founder and editor-in-chief of the award-winning magazine Clarkesworld.
  • C. David Nicholson
    David Nicholson is a historic Kentucky bourbon whiskey brand known for its traditional, full-bodied style and long-standing presence in the American whiskey market.
  • D. Cliff Morgan
    Cliff Morgan was a legendary Welsh rugby union fly-half renowned for his playmaking brilliance for Cardiff, Wales, and the British & Irish Lions, later becoming a prominent sports broadcaster.
  • E. Gareth Walters
    Gareth Walters was a Welsh composer and music educator known for his lyrical orchestral and choral works in the mid-20th century.
  • 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_69d822ea8b7c819097dfadf3d45545e6 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decf32666081908e84f985c47eb963 completed April 14, 2026, 11:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe64f6c6148190941b05d06d4dc54d completed May 8, 2026, 10:34 p.m.
Created at: April 10, 2026, 1:34 a.m.