Triple
T18820453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | feather theme |
E460247
|
entity |
| Predicate | hasVisualAssociation |
P126424
|
FINISHED |
| Object | floating feather in Forrest Gump |
—
|
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: floating feather in Forrest Gump | Statement: [feather theme, hasVisualAssociation, floating feather in Forrest Gump]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVisualAssociation Context triple: [feather theme, hasVisualAssociation, floating feather in Forrest Gump]
-
A.
hasVisuals
chosen
Indicates that one entity includes, displays, or is associated with visual elements or imagery related to another entity.
-
B.
visuallyDefines
Indicates that one entity establishes or clarifies the appearance, form, or visual characteristics of another entity.
-
C.
hasVisualImpact
Indicates that one entity affects or influences the visual appearance or aesthetic perception of another.
-
D.
hasContrastingRelationshipWith
Indicates a relationship in which two entities are opposed, divergent, or markedly different in qualities, roles, or effects.
-
E.
visualizedIn
Indicates that something is represented or depicted within a particular visual medium, view, or visualization.
- 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a6b9be988190b5e3804c39dc7dd9 |
completed | April 20, 2026, 4:08 a.m. |
| PD | Predicate disambiguation | batch_69e48d1b10ec8190985c6fb5766ff981 |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:55 a.m.