Triple

T26758521
Position Surface form Disambiguated ID Type / Status
Subject Bob Bennett E674734 entity
Predicate coreThemeInvolvingCharacter P30025 FINISHED
Object truth-telling 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: truth-telling | Statement: [Bob Bennett, coreThemeInvolvingCharacter, truth-telling]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: coreThemeInvolvingCharacter
Context triple: [Bob Bennett, coreThemeInvolvingCharacter, truth-telling]
  • A. themeInvolvingCharacter chosen
    Indicates that a theme, motif, or abstract concept centrally involves or is significantly shaped by a particular character.
  • B. mainThemeCharacter
    Indicates that a character serves as the central or primary figure associated with the main theme of a work or narrative.
  • C. characterTheme
    Indicates that a particular theme, motif, or conceptual focus is associated with a given character.
  • D. thematicCharacter
    Indicates that an entity serves as a central or recurring figure embodying key themes or motifs within a narrative or discourse.
  • E. hasMainThemeCharacter
    Indicates that a work (such as a story, film, or game) features a specific character as its central or primary thematic focus.
  • 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_69eecda6e9dc81908452fab3ba17ed9b completed April 27, 2026, 2:44 a.m.
NER Named-entity recognition batch_69f621fcea1481909b6f8b3af1ee6820 completed May 2, 2026, 4:10 p.m.
PD Predicate disambiguation batch_69f620debeb48190b7db395fb86cf8d9 completed May 2, 2026, 4:05 p.m.
Created at: April 27, 2026, 3:56 a.m.