Triple
T28106058
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waterloo Bridge, Sunlight in the Fog |
E710364
|
entity |
| Predicate | portraysLight |
P172335
|
FINISHED |
| Object | diffused sunlight |
—
|
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: diffused sunlight | Statement: [Waterloo Bridge, Sunlight in the Fog, portraysLight, diffused sunlight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portraysLight Context triple: [Waterloo Bridge, Sunlight in the Fog, portraysLight, diffused sunlight]
-
A.
portraysLighting
chosen
Indicates that one entity visually represents or depicts the lighting conditions or illumination effects of another entity.
-
B.
preferredLight
Indicates that one entity favors or is best suited to a particular lighting condition or level of illumination.
-
C.
portraysProduct
Indicates that one entity visually or narratively represents, depicts, or features a particular product.
-
D.
focusesLight
Indicates that one entity concentrates or directs light onto a specific area, object, or target.
-
E.
roleAtIllumination
Indicates that an entity holds or held a specific role or position at the organization Illumination.
- 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_69ef9b71fdb081908b4a61cd7ff147c1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f7b2f3a104819098ddd8909eaf596c |
completed | May 3, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f7b1b8a9fc8190a1279e67a2d12707 |
completed | May 3, 2026, 8:36 p.m. |
Created at: April 27, 2026, 9:08 p.m.