Triple

T20080607
Position Surface form Disambiguated ID Type / Status
Subject Snatch (TV series) E499988 entity
Predicate starring P1507 FINISHED
Object Ed Westwick 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: Ed Westwick | Statement: [Snatch (TV series), starring, Ed Westwick]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ed Westwick
Context triple: [Snatch (TV series), starring, Ed Westwick]
  • A. Ed Westwick chosen
    Ed Westwick is an English actor best known for his role as Chuck Bass on the television series "Gossip Girl."
  • B. Robert Pattinson
    Robert Pattinson is an English actor best known for his roles as vampire Edward Cullen in the Twilight film series and as the title character in the 2022 superhero film "The Batman."
  • C. Thomas Brodie-Sangster
    Thomas Brodie-Sangster is an English actor known for his roles in projects such as "Nanny McPhee," "The Maze Runner" series, and "Game of Thrones."
  • D. Dane DeHaan
    Dane DeHaan is an American actor known for his intense, often offbeat performances in films such as Chronicle, The Amazing Spider-Man 2, and Valerian and the City of a Thousand Planets.
  • E. Theo James
    Theo James is a British actor known for his roles in the Divergent film series and the HBO anthology series The White Lotus.
  • 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66557c19c8190b511857490bbd423 completed April 20, 2026, 5:41 p.m.
Created at: April 11, 2026, 3:41 p.m.