Triple

T22890822
Position Surface form Disambiguated ID Type / Status
Subject The Shadow Line E568034 entity
Predicate portrayedBy P1507 FINISHED
Object Anthony Sher 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: Anthony Sher | Statement: [The Shadow Line, portrayedBy, Anthony Sher]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anthony Sher
Context triple: [The Shadow Line, portrayedBy, Anthony Sher]
  • A. Anthony Sher chosen
    Anthony Sher was a renowned South African-born British actor and writer celebrated for his powerful stage performances, particularly with the Royal Shakespeare Company.
  • B. Edgar Jones
    Edgar Jones is a former professional basketball player best known for his high-flying athleticism in the NBA during the early 1980s.
  • C. Jeffrey Jones
    Jeffrey Jones is an American character actor best known for his roles in films such as "Ferris Bueller's Day Off," "Beetlejuice," and "Amadeus."
  • D. Tony Hibbert
    Tony Hibbert is a former English right-back best known for his long, one-club senior career at Everton FC in the Premier League.
  • E. Michael Boyd
    Michael Boyd is a Scottish theatre director best known for his leadership of the Royal Shakespeare Company and his acclaimed Shakespearean productions.
  • 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_69e2458c23ec81908fa2570692c6614f completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f17fc59e108190a22f90c2439830fb completed April 29, 2026, 3:49 a.m.
Created at: April 17, 2026, 3:40 p.m.