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.