Triple

T3276828
Position Surface form Disambiguated ID Type / Status
Subject Lady and the Tramp E68777 entity
Predicate director P255 FINISHED
Object Wilfred Jackson E100069 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: Wilfred Jackson | Statement: [Lady and the Tramp, director, Wilfred Jackson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wilfred Jackson
Context triple: [Lady and the Tramp, director, Wilfred Jackson]
  • A. Wilfred Jackson chosen
    Wilfred Jackson was an American animator and film director best known for his pioneering work on numerous classic Walt Disney animated features and shorts.
  • B. Ewart Brown
    Ewart Brown is a Bermudian physician and politician who served as Premier of Bermuda from 2006 to 2010 as leader of the Progressive Labour Party.
  • C. Frederick Carlton Lewis
    Frederick Carlton Lewis is an American former track and field athlete who won nine Olympic gold medals and became one of the sport’s most celebrated sprinters and long jumpers.
  • D. Herbert Jenkins
    Herbert Jenkins was a British publishing company best known for issuing popular fiction, including many works by P. G. Wodehouse.
  • E. George Taylor
    George Taylor was a Canadian architect best known for designing Toronto’s historic concert venue Massey Hall.
  • 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_69ad859b54f881909bf530d549caf2fd completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb0128f08819084644f3c8fda2596 completed March 8, 2026, 5:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69b34bb1c468819083b50b5858f8afe0 completed March 12, 2026, 11:26 p.m.
Created at: March 8, 2026, 3:10 p.m.