Triple

T21749372
Position Surface form Disambiguated ID Type / Status
Subject Milo Gibson E536871 entity
Predicate parent P120 FINISHED
Object Mel Gibson 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: Mel Gibson | Statement: [Milo Gibson, parent, Mel Gibson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mel Gibson
Context triple: [Milo Gibson, parent, Mel Gibson]
  • A. Mel Gibson chosen
    Mel Gibson is an American-born Australian actor and filmmaker best known for starring in the "Mad Max" and "Lethal Weapon" series and directing the Academy Award–winning film "Braveheart."
  • B. Stephen Lang
    Stephen Lang is an American actor known for his intense character roles in film, television, and theater, including prominent performances in movies like "Avatar" and "Public Enemies."
  • C. Joseph Gibson
    Joseph Gibson was a prominent local figure in North Carolina whose legacy is commemorated in the naming of the town of Gibsonville.
  • D. Russell Crowe
    Russell Crowe is an Academy Award–winning New Zealand–born actor renowned for intense, transformative performances in films such as Gladiator and A Beautiful Mind.
  • E. Mickey Rourke
    Mickey Rourke is an American actor and former boxer known for his intense, brooding performances in films such as "The Wrestler," "9½ Weeks," and "Angel Heart."
  • 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_69e0c46eab808190b848242d63a17c47 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f01a78bd908190b74e26ab1cc8788f completed April 28, 2026, 2:24 a.m.
Created at: April 16, 2026, 6:50 p.m.