Triple
T281151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Autoportrait au chapeau de paille |
E5356
|
entity |
| Predicate | depictsDirectionOfGaze |
P1101
|
FINISHED |
| Object | looking slightly to the side |
—
|
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: looking slightly to the side | Statement: [Autoportrait au chapeau de paille, depictsDirectionOfGaze, looking slightly to the side]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictsDirectionOfGaze Context triple: [Autoportrait au chapeau de paille, depictsDirectionOfGaze, looking slightly to the side]
-
A.
depicts
Indicates that one entity visually represents, portrays, or shows another entity.
-
B.
depictsPerson
Indicates that one entity visually represents or portrays a specific person.
-
C.
orientation
chosen
Indicates the relative directional alignment or facing of one entity with respect to another or to a reference frame.
-
D.
containsVisionOf
Indicates that one entity includes, depicts, or embodies a visual representation or image of another entity.
-
E.
directed
Indicates that one entity served as the director or guiding authority responsible for overseeing and controlling the actions or production involving 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_69a257e6c8788190987dfe705ca2912a |
completed | Feb. 28, 2026, 2:50 a.m. |
| NER | Named-entity recognition | batch_69a25e0a23c0819083abee28b2dea49c |
completed | Feb. 28, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_69a25b77e028819087e606fc321219f7 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:59 a.m.