Triple

T22731185
Position Surface form Disambiguated ID Type / Status
Subject Michael Cudlitz E562137 entity
Predicate name P16 FINISHED
Object Michael Cudlitz 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: Michael Cudlitz | Statement: [Michael Cudlitz, name, Michael Cudlitz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Cudlitz
Context triple: [Michael Cudlitz, name, Michael Cudlitz]
  • A. Michael Cudlitz chosen
    Michael Cudlitz is an American actor best known for his television roles in gritty police and military dramas, including Southland and The Walking Dead.
  • B. Geof Darrow
    Geof Darrow is an American comic book artist renowned for his hyper-detailed, intricately violent artwork on titles like Hard Boiled and Shaolin Cowboy, as well as his design work for films such as The Matrix.
  • C. Bryan Hitch
    Bryan Hitch is a British comic book artist renowned for his highly detailed, cinematic style on titles such as The Authority, The Ultimates, and various Marvel and DC series.
  • D. Ron Marz
    Ron Marz is an American comic book writer best known for his work on titles such as Green Lantern, Silver Surfer, and Witchblade.
  • E. Matt Kindt
    Matt Kindt is an American comic book writer and artist known for his intricate, genre-bending graphic novels and espionage-themed series such as "Mind MGMT."
  • 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_69e24550859c81908727d91efc3a81b4 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1792de040819093aa904bf751a788 completed April 29, 2026, 3:21 a.m.
Created at: April 17, 2026, 3:21 p.m.