Triple

T13148348
Position Surface form Disambiguated ID Type / Status
Subject Cocaine Bear E312397 entity
Predicate producer P490 FINISHED
Object Christopher Miller E81463 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: Christopher Miller | Statement: [Cocaine Bear, producer, Christopher Miller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Christopher Miller
Context triple: [Cocaine Bear, producer, Christopher Miller]
  • A. Christopher Miller chosen
    Christopher Miller is an American filmmaker, writer, and producer best known for his collaborative work with Phil Lord on inventive, genre-bending films and television series such as "The Lego Movie" and "21 Jump Street."
  • B. Christopher Miller
    Christopher Miller is a member of the Disney family, known primarily as the son of Diane Disney Miller and grandson of Walt Disney.
  • C. 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."
  • D. Scott Gilman
    Scott Gilman is a musician best known as a member of the British-American rock band Foreigner.
  • E. Richard Dale Snyder
    Richard Dale Snyder is an American businessman and Republican politician who served as the 48th governor of Michigan from 2011 to 2019.
  • 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_69d806aabde48190899e13e41659cae5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98bd0f5b08190ab700c5de1c8e138 completed April 10, 2026, 11:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6eae834908190aecb825db1d705ff completed May 3, 2026, 6:27 a.m.
Created at: April 9, 2026, 9:11 p.m.