Triple

T17884251
Position Surface form Disambiguated ID Type / Status
Subject Grant Morrison E447161 entity
Predicate employer P7 FINISHED
Object Marvel Comics 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: Marvel Comics | Statement: [Grant Morrison, employer, Marvel Comics]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marvel Comics
Context triple: [Grant Morrison, employer, Marvel Comics]
  • A. Marvel Comics chosen
    Marvel Comics is a major American comic book publisher best known for creating the Marvel Universe, home to iconic superheroes such as Spider-Man, Iron Man, the X-Men, and Captain America.
  • B. Marvel
    Marvel is a surname most prominently associated with American actress Elizabeth Marvel, known for her work in film, television, and theater.
  • C. DC Comics
    DC Comics is a major American comic book publisher best known for iconic superhero characters such as Superman, Batman, and Wonder Woman.
  • D. Atlas Comics
    Atlas Comics was a 1950s American comic book publisher that served as the direct predecessor to what later became Marvel Comics.
  • E. DC Entertainment
    DC Entertainment is a media company and subsidiary of Warner Bros. responsible for managing and developing film, television, and other adaptations of DC Comics properties.
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49c11530881908ad98fbd0a52b1c3 completed April 19, 2026, 9:10 a.m.
Created at: April 10, 2026, 10:18 a.m.