Triple

T20949649
Position Surface form Disambiguated ID Type / Status
Subject Superman: Unbound E515944 entity
Predicate basedOnWorkBy P2806 FINISHED
Object Geoff Johns 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: Geoff Johns | Statement: [Superman: Unbound, basedOnWorkBy, Geoff Johns]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Geoff Johns
Context triple: [Superman: Unbound, basedOnWorkBy, Geoff Johns]
  • A. Geoff Johns chosen
    Geoff Johns is a prominent American comic book writer and producer best known for revitalizing major DC Comics characters and serving as a key architect of the modern DC Universe.
  • B. Mark Waid
    Mark Waid is an American comic book writer best known for influential runs on titles like The Flash, Kingdom Come, and various Justice League stories for DC Comics.
  • C. Scott Snyder
    Scott Snyder is an American comic book writer best known for his acclaimed work on Batman titles for DC Comics, including "Detective Comics" and "Batman."
  • D. Andy Diggle
    Andy Diggle is a British comic book writer and former editor known for his work on titles such as "The Losers," "Green Arrow: Year One," and various 2000 AD stories.
  • E. Brian Azzarello
    Brian Azzarello is an American comic book writer best known for his gritty, noir-influenced work on series such as 100 Bullets and numerous titles for DC and its Vertigo imprint.
  • 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_69e0b4fcd678819087a304291f14330a completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fadc08148190b4ff710f94462a26 completed April 21, 2026, 4:19 a.m.
Created at: April 16, 2026, 1:18 p.m.