Triple

T10997713
Position Surface form Disambiguated ID Type / Status
Subject Eben Oleson E259923 entity
Predicate creator P184 FINISHED
Object Steve Niles E259299 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: Steve Niles | Statement: [Eben Oleson, creator, Steve Niles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steve Niles
Context triple: [Eben Oleson, creator, Steve Niles]
  • A. Steve Niles chosen
    Steve Niles is an American comic book writer and novelist best known for his influential horror work, including co-creating the vampire series "30 Days of Night."
  • B. Matt Wagner
    Matt Wagner is an American comic book writer and artist best known for creating the series Grendel and Mage and for his influential work across independent and mainstream comics.
  • C. Greg Rucka
    Greg Rucka is an American comic book writer and novelist known for his work on titles like "Batman," "Wonder Woman," and "Lazarus," as well as for adapting his own comic "The Old Guard" into a film screenplay.
  • D. Bill Willingham
    Bill Willingham is an American comic book writer and artist best known as the creator of the acclaimed fantasy series "Fables."
  • E. Warren Ellis
    Warren Ellis is a British comic book writer and novelist renowned for influential works like "Transmetropolitan," "Planetary," and numerous groundbreaking series for major publishers.
  • 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_69d6aa8a6a548190a750f944ccdc8064 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d796d20b448190958331705de3a9be completed April 9, 2026, 12:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3a9644ff08190a3005e4f6a8243fe completed April 18, 2026, 3:55 p.m.
Created at: April 8, 2026, 9:24 p.m.