Triple
T10784700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portrait of Charles V with a Dog |
E254422
|
entity |
| Predicate | depictsPosition |
P82741
|
FINISHED |
| Object | full-length standing pose |
—
|
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: full-length standing pose | Statement: [Portrait of Charles V with a Dog, depictsPosition, full-length standing pose]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictsPosition Context triple: [Portrait of Charles V with a Dog, depictsPosition, full-length standing pose]
-
A.
depictedNear
Indicates that two entities are shown in close spatial proximity to each other within the same depiction or scene.
-
B.
positionDescribed
chosen
Indicates that a position, location, or spatial arrangement of an entity is explicitly specified or characterized, typically in descriptive terms.
-
C.
depicts
Indicates that one entity visually represents, portrays, or shows another entity.
-
D.
depictsView
Indicates that one entity visually represents or portrays the view, scene, or perspective of another entity.
-
E.
depictsPerson
Indicates that one entity visually represents or portrays a specific person.
- 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_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d732d2e7cc8190a4cb9a4d7c76ab15 |
completed | April 9, 2026, 5:02 a.m. |
| PD | Predicate disambiguation | batch_69d6f316940c819092a96c429629fdef |
completed | April 9, 2026, 12:30 a.m. |
Created at: April 8, 2026, 9:17 p.m.