Triple

T5692394
Position Surface form Disambiguated ID Type / Status
Subject Hannibal Lecter film series E125455 entity
Predicate mainCharacter P1183 FINISHED
Object Hannibal Lecter E130828 NE FINISHED

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 Lecter | Statement: [Hannibal Lecter film series, mainCharacter, Hannibal Lecter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hannibal Lecter
Context triple: [Hannibal Lecter film series, mainCharacter, Hannibal Lecter]
  • A. Hannibal Lecter chosen
    Hannibal Lecter is a brilliant but psychopathic cannibalistic serial killer and psychiatrist, best known as the chilling antagonist in Thomas Harris’s novels and their film adaptations.
  • B. Francis Dolarhyde
    Francis Dolarhyde is the fictional serial killer known as "The Tooth Fairy" in Thomas Harris's novel *Red Dragon* and its screen adaptations.
  • C. Michael Ripps
    Michael Ripps is a film editor known for his work on the movie "Stakeout."
  • D. Tom Ripley
    Tom Ripley is a charming yet deeply amoral con artist and serial imposter best known as the psychologically complex antihero of Patricia Highsmith’s crime novels.
  • E. Thomas Ripley
    Thomas Ripley was an 18th-century English architect and master carpenter known for his work on prominent country houses and public buildings, including contributions to Palladian architecture.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c0082bb19c8190823a4facd3cba79b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c023e678c48190824d35d276985311 completed March 22, 2026, 5:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07dd76f008190970c3b17ec8cbfd8 completed March 22, 2026, 11:40 p.m.
Created at: March 22, 2026, 3:44 p.m.