Triple

T18251389
Position Surface form Disambiguated ID Type / Status
Subject Titans E437098 entity
Predicate mainCharacter P1183 FINISHED
Object Conner Kent 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: Conner Kent | Statement: [Titans, mainCharacter, Conner Kent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Conner Kent
Context triple: [Titans, mainCharacter, Conner Kent]
  • A. Conner Kent chosen
    Conner Kent is a DC Comics superhero better known as Superboy, a clone combining Kryptonian and human DNA who serves as a prominent member of the Superman family and various teen hero teams.
  • B. Conner
    Conner is a municipality located in the province of Apayao in the Cordillera Administrative Region of the Philippines.
  • C. Conner
    Conner is the surname of American gymnast and Olympic gold medalist Bart Conner.
  • D. Grayson Kent
    Grayson Kent is a central character in the legal dramedy "Drop Dead Diva," portrayed as a charming and principled attorney who serves as the main love interest of the show's protagonist.
  • E. Conner Wallace
    Conner Wallace is a fictional character portrayed by actor Eddie Cahill, best known as a central figure in the legal drama series "Conviction."
  • 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_69d8b91104e08190a8241f7d260a5162 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4fd8124648190ae7fc9f1fc5cf9bd completed April 19, 2026, 4:06 p.m.
Created at: April 10, 2026, 10:33 a.m.