Triple
T3119933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | icon of Our Lady of Kazan (copy) |
E65157
|
entity |
| Predicate | iconographicSchool |
P37204
|
FINISHED |
| Object | Russian iconography |
—
|
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: Russian iconography | Statement: [icon of Our Lady of Kazan (copy), iconographicSchool, Russian iconography]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: iconographicSchool Context triple: [icon of Our Lady of Kazan (copy), iconographicSchool, Russian iconography]
-
A.
iconographyType
Indicates the specific kind or category of visual symbolism or imagery used to represent something.
-
B.
iconographyFeature
Indicates a visual element or motif that appears as a distinct feature within a work’s iconography.
-
C.
iconographicFunction
Indicates the symbolic or representational role that something serves within an image or visual composition.
-
D.
iconographyInfluence
chosen
Indicates that one entity’s visual symbols, motifs, or stylistic elements have shaped or informed the iconographic style or imagery of another entity.
-
E.
iconographicVariant
Indicates that one representation is an alternative or variant visual depiction of another within an iconographic tradition or system.
- 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_69ad857fcc088190b0c4d45a5cde6f61 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada4eb6a6081909df41f67999eb4ff |
completed | March 8, 2026, 4:33 p.m. |
| PD | Predicate disambiguation | batch_69ad9df455088190940ad04419772dc8 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:04 p.m.