Triple

T21307887
Position Surface form Disambiguated ID Type / Status
Subject Michelle Dessler E525247 entity
Predicate employer P7 FINISHED
Object CTU Division 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: CTU Division | Statement: [Michelle Dessler, employer, CTU Division]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CTU Division
Context triple: [Michelle Dessler, employer, CTU Division]
  • A. CTU
    CTU is a major technical university in Prague known for its engineering and technology programs.
  • B. CTU chosen
    CTU is a commonly used abbreviation that can refer to various organizations or concepts, most notably the Counter Terrorist Unit in the television series "24."
  • C. CTU New York
    CTU New York is a fictional Counter Terrorist Unit branch in the "24" television series, serving as a key hub for U.S. national security operations in New York City.
  • D. Division 44
    Division 44 is a division of the American Psychological Association focused on research, practice, and advocacy related to sexual orientation and gender diversity.
  • E. Division 45
    Division 45 is a division of the American Psychological Association dedicated to advancing psychological research, practice, and education related to culture, ethnicity, and race.
  • 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_69e0b518b8948190ad69cf9a8784d397 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e75aa7b2f08190bea46f0107bcc045 completed April 21, 2026, 11:08 a.m.
Created at: April 16, 2026, 4:05 p.m.