Triple

T9034775
Position Surface form Disambiguated ID Type / Status
Subject Anakin Skywalker E216463 entity
Predicate portrayedBy P1507 FINISHED
Object David Prowse E209453 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: David Prowse | Statement: [Anakin Skywalker, portrayedBy, David Prowse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Prowse
Context triple: [Anakin Skywalker, portrayedBy, David Prowse]
  • A. David Prowse chosen
    David Prowse was an English bodybuilder and actor best known for physically portraying Darth Vader in the original Star Wars trilogy.
  • B. Peter Mayhew
    Peter Mayhew was an English-American actor best known for portraying the Wookiee Chewbacca in the original Star Wars film series.
  • C. Anthony Daniels
    Anthony Daniels is an English actor best known for portraying the droid C-3PO throughout the Star Wars film series.
  • D. Jorge Luke
    Jorge Luke was a Mexican actor known for his roles in 1970s and 1980s films, often portraying intense and complex characters in both Mexican and international cinema.
  • E. Billy Dee Williams
    Billy Dee Williams is an American actor best known for his charismatic roles in films such as "The Empire Strikes Back" and "Return of the Jedi," where he portrayed Lando Calrissian.
  • 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_69ca83d10b608190b2b2f8e0a7faaf14 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc6abf4af481908d21245332329d99 completed April 1, 2026, 12:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfdbce352c8190b5862d0cc103bfdb completed April 3, 2026, 3:25 p.m.
Created at: March 30, 2026, 7:08 p.m.