Triple

T12458600
Position Surface form Disambiguated ID Type / Status
Subject Madagascar E297725 entity
Predicate producer P490 FINISHED
Object Mark Swift E223086 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: Mark Swift | Statement: [Madagascar, producer, Mark Swift]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Swift
Context triple: [Madagascar, producer, Mark Swift]
  • A. Mark Swift chosen
    Mark Swift is a film producer best known for his work on animated and genre movies, including "Captain Underpants: The First Epic Movie."
  • B. Jeremy Swift
    Jeremy Swift is an English actor known for his character roles in film and television, including appearances in projects like "Downton Abbey" and "Ted Lasso."
  • C. Frank Swift
    Frank Swift was an English professional football goalkeeper best known for his long and successful career with Manchester City and for representing England before his death in the 1958 Munich air disaster.
  • D. David Swift
    David Swift was an American screenwriter, director, and producer best known for creating and writing classic family films and television shows, including the original 1961 version of "The Parent Trap."
  • E. Scott Banister
    Scott Banister is an American entrepreneur and angel investor known for co-founding IronPort and early involvement with companies like PayPal and Facebook.
  • 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_69d6ada270808190b1a2b2e7b02bb426 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94da46a588190bc888fafd6d1eb5d completed April 10, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63f1b0a3081909cf22970586755e9 completed May 2, 2026, 6:14 p.m.
Created at: April 8, 2026, 9:56 p.m.