Triple

T22481832
Position Surface form Disambiguated ID Type / Status
Subject Bella Crawford E555784 entity
Predicate appearsIn P795 FINISHED
Object Hannibal 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: Hannibal | Statement: [Bella Crawford, appearsIn, Hannibal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hannibal
Context triple: [Bella Crawford, appearsIn, Hannibal]
  • A. Hannibal
    Hannibal is a character in the play "The Curious Savage," known as one of the eccentric residents of a sanatorium whose quirks highlight themes of sanity, kindness, and societal values.
  • B. Hannibal
    Hannibal is the cigar-chomping, disguise-loving leader of the A-Team in the 1980s American television series of the same name.
  • C. Hannibal
    Hannibal is a historic Mississippi River town in Missouri best known as the boyhood home of Mark Twain and the setting for many of his classic works.
  • D. Hannibal chosen
    Hannibal is a psychological horror novel by Thomas Harris that continues the story of FBI agent Clarice Starling and the cannibalistic serial killer Dr. Hannibal Lecter.
  • E. C. Hannibal
    C. Hannibal is a songwriter known for contributing to the R&B track "Before I Let You Go."
  • 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_69e11e53897c819088863779f8c50bb0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15c397b248190b36c2fbfa6489693 completed April 29, 2026, 1:17 a.m.
Created at: April 16, 2026, 8:49 p.m.