Triple
T21614139
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boy with a Basket of Fruit |
E533388
|
entity |
| Predicate | depictedObject |
P46781
|
FINISHED |
| Object | grapes |
—
|
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: grapes | Statement: [Boy with a Basket of Fruit, depictedObject, grapes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictedObject Context triple: [Boy with a Basket of Fruit, depictedObject, grapes]
-
A.
depictedSubject
Indicates that one entity visually represents or portrays another entity as its subject in an image or depiction.
-
B.
depictsPerson
Indicates that one entity visually represents or portrays a specific person.
-
C.
depictedAbove
Indicates that one entity is visually represented in an image, illustration, or diagram that is positioned above another referenced element in a layout or document.
-
D.
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.
-
E.
depictionElement
chosen
Indicates that one entity is an element or component that appears within the visual or representational depiction 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_69e0c46411108190bba0d4176dffc9f3 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef3ba9aca48190b5180eefd61a9fdc |
completed | April 27, 2026, 10:34 a.m. |
| PD | Predicate disambiguation | batch_69e69665fe8c8190af7e38785db188b2 |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:33 p.m.