Triple

T23515413
Position Surface form Disambiguated ID Type / Status
Subject Get Smart E574346 entity
Predicate character P662 FINISHED
Object Maxwell Smart 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: Maxwell Smart | Statement: [Get Smart, character, Maxwell Smart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maxwell Smart
Context triple: [Get Smart, character, Maxwell Smart]
  • A. Maxwell Smart chosen
    Maxwell Smart is the bumbling yet oddly effective secret agent protagonist of the classic satirical spy television series "Get Smart."
  • B. John "Hannibal" Smith
    John "Hannibal" Smith is the cigar-chomping, disguise-loving mastermind and leader of the A-Team, known for his brilliant tactical planning and love of a good plan coming together.
  • C. Heller Taccone
    Heller Taccone is a family surname associated with individuals such as Wylie Red Heller Taccone.
  • D. Hank Mann
    Hank Mann was a prolific silent film comedian and character actor, best known as one of the original Keystone Cops and for his numerous supporting roles in early Hollywood comedies.
  • E. Napoleon Solo
    Napoleon Solo is a suave, resourceful American CIA agent who teams up with a KGB counterpart to thwart international threats in the 1960s-set spy adventure "The Man from U.N.C.L.E."
  • 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_69e245bb3dcc8190ba9a2b35972b58d0 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1aa81ab4c8190b85c8f80754020ea completed April 29, 2026, 6:51 a.m.
Created at: April 17, 2026, 6:08 p.m.