Triple
T28729703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bernardo Bellotto |
E730622
|
entity |
| Predicate | courtPainterTo |
P77472
|
FINISHED |
| Object | Augustus III of Poland |
—
|
NE NERFINISHED |
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: Augustus III of Poland | Statement: [Bernardo Bellotto, courtPainterTo, Augustus III of Poland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: courtPainterTo Context triple: [Bernardo Bellotto, courtPainterTo, Augustus III of Poland]
-
A.
courtPainterOf
chosen
Indicates that one entity serves as the official painter appointed to the court of another entity.
-
B.
courtPatron
Indicates that one entity serves as a patron, supporter, or sponsor to another within a courtly or formal institutional context.
-
C.
painter
Indicates that one entity creates paintings of, or is responsible for painting, another entity.
-
D.
associatedPainter
Indicates a relationship where a painter is linked or connected to something, such as a work, place, or subject, as the artist associated with it.
-
E.
courtDesignBy
Indicates that a court was designed or planned by a particular agent or designer.
- 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_69f043eae0908190b28ce314686247d7 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f67257b0448190a13011af81c81449 |
completed | May 2, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69f66ec5bf508190ad088b89455252bd |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 28, 2026, 5:57 a.m.