Triple
T4848206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House of Dionysus mosaic |
E108344
|
entity |
| Predicate | depictsScene |
P1581
|
FINISHED |
| Object | Dionysus riding a panther |
—
|
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: Dionysus riding a panther | Statement: [House of Dionysus mosaic, depictsScene, Dionysus riding a panther]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictsScene Context triple: [House of Dionysus mosaic, depictsScene, Dionysus riding a panther]
-
A.
depicts
chosen
Indicates that one entity visually represents, portrays, or shows another entity.
-
B.
partOfScene
Indicates that one entity functions as a component or element within a larger scene or setting involving another entity.
-
C.
depictionAction
Indicates an action in which one entity visually represents, illustrates, or portrays another entity.
-
D.
depictionContext
Indicates the situational or environmental setting in which something is depicted or represented.
-
E.
depictedNear
Indicates that two entities are shown in close spatial proximity to each other within the same depiction or scene.
- 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_69bd4409b264819085ab855f3eb5381a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ddd17d881909f7731ff2b460e83 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2557388190a2d15571bacd24f3 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:25 p.m.