Triple

T7907957
Position Surface form Disambiguated ID Type / Status
Subject Mark Millar E183623 entity
Predicate employer P7 FINISHED
Object Image Comics E447167 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: Image Comics | Statement: [Mark Millar, employer, Image Comics]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Image Comics
Context triple: [Mark Millar, employer, Image Comics]
  • A. Image Comics chosen
    Image Comics is a major American comic book publisher founded in 1992 by a group of superstar artists seeking creator-owned control, known for titles like Spawn, The Walking Dead, and Saga.
  • B. Icon Comics
    Icon Comics is a creator-owned imprint of Marvel Comics established to publish work by high-profile writers and artists outside the main Marvel Universe.
  • C. Fantagraphics Books
    Fantagraphics Books is an American independent publisher renowned for its high-quality editions of classic and alternative comics and graphic novels.
  • D. IDW Publishing
    IDW Publishing is an American comic book and graphic novel publisher known for producing licensed titles based on popular media franchises.
  • E. Titan Comics
    Titan Comics is a British comic book publisher known for producing licensed titles based on popular media franchises, including the long-running Doctor Who series.
  • 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_69ca828dec0c81908b8f55a4dbbb53ff completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3a59de00819099f1ce02bb469e75 completed March 31, 2026, 3:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5bd0024c81909679a45612bcb1a7 completed March 31, 2026, 5:29 a.m.
Created at: March 30, 2026, 5:03 p.m.