Triple

T17884227
Position Surface form Disambiguated ID Type / Status
Subject Grant Morrison E447161 entity
Predicate notableWork P4 FINISHED
Object Animal Man 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: Animal Man | Statement: [Grant Morrison, notableWork, Animal Man]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Animal Man
Context triple: [Grant Morrison, notableWork, Animal Man]
  • A. Animal Man chosen
    Animal Man is a DC Comics superhero, often associated with mature-reader Vertigo stories, who can mimic the abilities of any animal and frequently explores metafictional and philosophical themes.
  • B. Plastic Man
    Plastic Man is the nickname of former NBA player Stacey Augmon, known for his exceptional defensive skills and long, flexible frame.
  • C. Plastic Man
    Plastic Man is a classic DC Comics superhero known for his comedic tone and extraordinary ability to stretch and morph his body into virtually any shape.
  • D. Monkey Man
    "Monkey Man" is a blues-rock song by the Rolling Stones, featured on their 1969 album *Let It Bleed*.
  • E. Monkey Man
    Monkey Man is an action-thriller film directed by Dev Patel in his first role behind the camera, following a vengeance-driven protagonist in a gritty, contemporary Indian setting.
  • 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.