Triple
T8578910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Boulevard Montmartre at Night |
E203117
|
entity |
| Predicate | depiction style |
P9800
|
FINISHED |
| Object | atmospheric effects |
—
|
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: atmospheric effects | Statement: [The Boulevard Montmartre at Night, depiction style, atmospheric effects]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depiction style Context triple: [The Boulevard Montmartre at Night, depiction style, atmospheric effects]
-
A.
depictionType
chosen
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.
artisticDepiction
Indicates that one entity visually represents, portrays, or illustrates another in an artistic medium.
-
D.
depictionContext
Indicates the situational or environmental setting in which something is depicted or represented.
-
E.
depictionAction
Indicates an action in which one entity visually represents, illustrates, or portrays 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_69ca8328ebe481909a8c038fa79959b4 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbea9a0708819084cb8b8d84017864 |
completed | March 31, 2026, 3:39 p.m. |
| PD | Predicate disambiguation | batch_69cbd11b13108190b07f8f161425a585 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:22 p.m.