Triple
T12373916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Giovanna Bellelli |
E295072
|
entity |
| Predicate | positionInPainting |
P57195
|
FINISHED |
| Object | standing daughter |
—
|
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: standing daughter | Statement: [Giovanna Bellelli, positionInPainting, standing daughter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInPainting Context triple: [Giovanna Bellelli, positionInPainting, standing daughter]
-
A.
paintingAlignment
Indicates the orientation or directional arrangement of a painting relative to a reference frame or surface.
-
B.
paintedIn
Indicates that an artwork or object was created or executed using paint within a specific time period or at a particular location.
-
C.
iconographicPosition
chosen
Indicates the relative placement or arrangement of elements within an image or visual composition, specifying where something appears in the iconographic layout.
-
D.
placeOfDepiction
Indicates the location or setting where the depicted subject is shown as being situated in the representation.
-
E.
paintedOn
Indicates that one entity has been applied as paint onto the surface of another entity.
- 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_69d6ab6d8a4081908636601e69ddf262 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d942a2d6e08190a13c7ff89af09354 |
completed | April 10, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69d93ecf6b548190a394b6b56a0c1c68 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.