Triple

T14957116
Position Surface form Disambiguated ID Type / Status
Subject Buddy E372959 entity
Predicate directedBy P7373 FINISHED
Object Jon Favreau E48163 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: Jon Favreau | Statement: [Buddy, directedBy, Jon Favreau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jon Favreau
Context triple: [Buddy, directedBy, Jon Favreau]
  • A. Jon Favreau chosen
    Jon Favreau is an American filmmaker and actor known for directing blockbuster films such as Iron Man and The Jungle Book and for creating the Star Wars series The Mandalorian.
  • B. Avri Roel Downey
    Avri Roel Downey is the daughter of actor Robert Downey Jr. and producer Susan Downey.
  • C. Peyton Reed
    Peyton Reed is an American film director known for helming major studio comedies and Marvel superhero films, including entries in the Ant-Man series.
  • D. Chris Miller
    Chris Miller is an American writer best known for co-writing the screenplay to the influential 1978 comedy film "National Lampoon's Animal House."
  • E. Jon Favreau (speechwriter)
    Jon Favreau is an American political commentator and former Director of Speechwriting for President Barack Obama, known for crafting many of Obama's most notable speeches and co-founding the media company Crooked Media.
  • 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_69d85cca979481908747d2a81eba1cea completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded6cc73848190ac181782b20dc838 completed April 15, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe7e9e74fc8190bdd10a25c39829f3 completed May 9, 2026, 12:23 a.m.
Created at: April 10, 2026, 2:40 a.m.