Triple

T17434960
Position Surface form Disambiguated ID Type / Status
Subject The Sicilian E423976 entity
Predicate narrativeRoleOfMichaelCorleone P101050 FINISHED
Object exile in Sicily LITERAL 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: exile in Sicily | Statement: [The Sicilian, narrativeRoleOfMichaelCorleone, exile in Sicily]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: narrativeRoleOfMichaelCorleone
Context triple: [The Sicilian, narrativeRoleOfMichaelCorleone, exile in Sicily]
  • A. narrativeRoleInSeries
    Indicates the specific narrative function or role an entity plays within a particular series or serialized work.
  • B. roleInManOnFire
    Indicates that an entity has a role or participation in the work titled "Man on Fire."
  • C. inNarrativeRole chosen
    Indicates that one entity participates in relation to another by occupying a specific narrative function or role within a story or discourse.
  • D. godfather
    Indicates a person who serves as a male sponsor, mentor, or protector to another, often in a ceremonial, familial, or organizational context.
  • E. metaNarrativeRole
    Indicates the narrative function or role that one element (such as a character, voice, or device) plays in commenting on, framing, or reflecting the story itself at a meta-level.
  • F. None of above.

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_69d889d88b6081908bada047f5b3ba51 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4490361c081908fd24f9a812f212c completed April 19, 2026, 3:16 a.m.
PD Predicate disambiguation batch_69e3b030eac481909b8402719cc3102e completed April 18, 2026, 4:24 p.m.
Created at: April 10, 2026, 5:46 a.m.