Triple

T21900177
Position Surface form Disambiguated ID Type / Status
Subject Jack Crusher E540786 entity
Predicate portrayedBy P1507 FINISHED
Object Ed Speleers 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 Speleers | Statement: [Jack Crusher, portrayedBy, Ed Speleers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ed Speleers
Context triple: [Jack Crusher, portrayedBy, Ed Speleers]
  • A. Ed Speleers chosen
    Ed Speleers is an English actor best known for his roles in the fantasy film "Eragon" and the television series "Downton Abbey" and "Outlander."
  • B. Luke Treadaway
    Luke Treadaway is an English actor known for his roles in films such as "Attack the Block" and "A Street Cat Named Bob," as well as for his work on stage and television.
  • C. Nicholas Hoult
    Nicholas Hoult is an English actor known for his versatile roles in films such as "About a Boy," the "X-Men" series, and "Mad Max: Fury Road," as well as the TV series "Skins" and "The Great."
  • D. Joe Alwyn
    Joe Alwyn is a British actor known for his roles in films such as "Operation Finale," "The Favourite," and "Billy Lynn's Long Halftime Walk."
  • E. Michiel Huisman
    Michiel Huisman is a Dutch actor and musician known for roles in international film and television, including series like Game of Thrones and The Haunting of Hill House.
  • 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_69e0c47b4e8c81908c8076eaa4c8e4f2 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f11fca2bf88190b2a5b912aa102513 completed April 28, 2026, 8:59 p.m.
Created at: April 16, 2026, 7:07 p.m.