Triple
T5090585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terrasse du café le soir |
E114741
|
entity |
| Predicate | depictionAngle |
P60678
|
FINISHED |
| Object | street-level perspective |
—
|
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: street-level perspective | Statement: [Terrasse du café le soir, depictionAngle, street-level perspective]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictionAngle Context triple: [Terrasse du café le soir, depictionAngle, street-level perspective]
-
A.
depictionType
Indicates the specific manner or style in which something is visually represented or depicted.
-
B.
depictionDetail
Indicates that one depiction provides additional detail, refinement, or a closer view of what is shown in another depiction.
-
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.
depictionAction
Indicates an action in which one entity visually represents, illustrates, or portrays another entity.
-
E.
depictionFocus
Indicates that a depiction (such as an image or illustration) is primarily focused on or centered around a particular entity or subject.
- F. None of above. chosen
Provenance (4 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_69bd443e941881908eb4e8c685b6f656 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd75407e6881908d00377a256ff37e |
completed | March 20, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69bd715c0a448190afc837c6c31dc6ab |
completed | March 20, 2026, 4:10 p.m. |
| PDg | Predicate description generation | batch_69bd72b8d7a88190ad53fae64f17e22c |
completed | March 20, 2026, 4:15 p.m. |
Created at: March 20, 2026, 1:40 p.m.