Triple
T17780627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rain (painting) |
E443883
|
entity |
| Predicate | hasBrushworkType |
P14919
|
FINISHED |
| Object | broad gestural strokes |
—
|
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: broad gestural strokes | Statement: [Rain (painting), hasBrushworkType, broad gestural strokes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBrushworkType Context triple: [Rain (painting), hasBrushworkType, broad gestural strokes]
-
A.
usesBrushworkType
chosen
Indicates that an entity employs or is characterized by a particular type or style of brushwork in its creation or execution.
-
B.
hasHandwritingOf
Indicates that one entity’s handwriting style or written text is attributed to, or produced by, another entity.
-
C.
hasTypicalInscriptionMethod
Indicates the usual or characteristic method by which inscriptions are applied or created on an object or surface.
-
D.
hasCarvingType
Indicates that one entity is associated with a specific type or style of carving applied to it.
-
E.
hasWallPaintingStyle
Indicates that an entity features or is associated with a particular style or type of wall painting.
- 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_69d8b9ef17708190bdf7e2adbf14ddc2 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4872152508190870a1765e0972ec1 |
completed | April 19, 2026, 7:41 a.m. |
| PD | Predicate disambiguation | batch_69e3d8d8e538819084f1584426b41d5e |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:12 a.m.