Triple
T25354593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke |
E635783
|
entity |
| Predicate | hasImageAssociation |
P136026
|
FINISHED |
| Object | soldier roles |
—
|
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: soldier roles | Statement: [Duke, hasImageAssociation, soldier roles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasImageAssociation Context triple: [Duke, hasImageAssociation, soldier roles]
-
A.
hasImageRole
Indicates that an image is associated with an entity in a specific functional or contextual role (e.g., thumbnail, icon, illustration).
-
B.
associatedWithMediaImage
chosen
Indicates a relationship where an entity is linked or connected to a specific media image, such as a photo, illustration, or graphic file.
-
C.
containsImage
Indicates that one entity includes or embeds an image as part of its content or structure.
-
D.
hasImageFeature
Indicates that an entity is associated with a specific visual characteristic or attribute extracted from an image.
-
E.
hasMainImageSource
Indicates that an entity is associated with a primary image file or URL that serves as its main visual representation.
- 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_69e75a9ac5d881909387ed766e20cd47 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f60c3b09488190ade1b69ff7f0df0e |
completed | May 2, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69f60b8461ac81908c5bd3d73eed59f4 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 21, 2026, 1:35 p.m.