Triple
T17953581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Asura |
E448889
|
entity |
| Predicate | isDepictedInArtForm |
P74686
|
FINISHED |
| Object | Hindu temple sculpture |
—
|
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: Hindu temple sculpture | Statement: [Asura, isDepictedInArtForm, Hindu temple sculpture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isDepictedInArtForm Context triple: [Asura, isDepictedInArtForm, Hindu temple sculpture]
-
A.
isDepictedInArtMovement
Indicates that an entity is portrayed or represented within artworks associated with a particular art movement.
-
B.
appearsInWorkOfArt
chosen
Indicates that an entity is depicted, represented, or otherwise featured within a particular work of art.
-
C.
isDepictedVia
Indicates that one entity is represented, illustrated, or shown by means of another entity, such as a specific medium, style, or method of depiction.
-
D.
artisticDepiction
Indicates that one entity visually represents, portrays, or illustrates another in an artistic medium.
-
E.
artworkType
Indicates the specific category or kind of artwork that characterizes the relationship between the subject and the artwork.
- 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_69d8b9f8cca8819099836916c56b7c95 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4afae2aa081909a59a8cd4f1d04e1 |
completed | April 19, 2026, 10:34 a.m. |
| PD | Predicate disambiguation | batch_69e3f8f2bd088190b1e22ad4d9cc8b13 |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:21 a.m.