Triple

T2308340
Position Surface form Disambiguated ID Type / Status
Subject High Noon E51892 entity
Predicate character P662 FINISHED
Object Frank Miller E225274 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: Frank Miller | Statement: [High Noon, character, Frank Miller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Miller
Context triple: [High Noon, character, Frank Miller]
  • A. Frank Miller chosen
    Frank Miller is an American comic book writer, artist, and film director best known for his dark, stylized works such as "The Dark Knight Returns," "Sin City," and "300."
  • B. Richard Sale
    Richard Sale was an American screenwriter, novelist, and film director active in mid-20th-century Hollywood.
  • C. Alan Moore
    Alan Moore is a British comic book writer and novelist renowned for groundbreaking works such as "Watchmen," "V for Vendetta," and "From Hell," which revolutionized the graphic novel medium.
  • D. Joe Gilliam
    Joe Gilliam was an American football quarterback best known for breaking racial barriers as one of the first Black starting quarterbacks in the NFL with the Pittsburgh Steelers in the 1970s.
  • E. Mike Mignola
    Mike Mignola is an American comic book artist and writer best known for creating the dark, folklore-infused Hellboy universe and for his distinctive, shadow-heavy visual style.
  • 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_69a88b0bb30c81908ded03b006d29387 completed March 4, 2026, 7:42 p.m.
NER Named-entity recognition batch_69abc607cf4881908ba4ea2a7f5dedc9 completed March 7, 2026, 6:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae8959d860819095ea3113e3d9264e completed March 9, 2026, 8:48 a.m.
Created at: March 4, 2026, 7:49 p.m.