Triple
T19896463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guler |
E478163
|
entity |
| Predicate | paintingMedium |
P18308
|
FINISHED |
| Object | miniature paintings on paper |
—
|
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: miniature paintings on paper | Statement: [Guler, paintingMedium, miniature paintings on paper]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: paintingMedium Context triple: [Guler, paintingMedium, miniature paintings on paper]
-
A.
artisticMedium
chosen
Indicates the material or technique used to create an artwork or artistic expression.
-
B.
cultMedium
Indicates that a particular medium is used to culture or grow a specified biological or experimental sample.
-
C.
paintingSettingOf
Indicates that a painting depicts or provides the visual setting or background context for another entity or scene.
-
D.
paintingProject
Indicates a relationship where an entity undertakes or is associated with the activity of creating, executing, or managing a painting-related task or assignment.
-
E.
artSpecialty
Indicates that an entity’s primary focus, expertise, or specialization is in a particular art form or artistic domain.
- 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_69d8e520682081909892916424699bd5 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6593dba78819082c8b80e65246171 |
completed | April 20, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69e537ecda248190895c96afb6243823 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:52 p.m.