Triple
T18952503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beauty (installation) |
E463687
|
entity |
| Predicate | viewerPositionAffects |
P127904
|
FINISHED |
| Object | visibility of rainbow |
—
|
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: visibility of rainbow | Statement: [Beauty (installation), viewerPositionAffects, visibility of rainbow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: viewerPositionAffects Context triple: [Beauty (installation), viewerPositionAffects, visibility of rainbow]
-
A.
hasViewingPointFor
chosen
Indicates that one entity serves as a vantage point or location from which another entity can be viewed or observed.
-
B.
viewpointNear
Indicates that one entity serves as a viewpoint or vantage location that is geographically close to another entity.
-
C.
viewerInteraction
Indicates that one entity engages with or responds to content presented by another entity, such as by viewing, reacting, or otherwise interacting with it.
-
D.
perspectiveOf
Indicates that something is expressed, depicted, or understood from the viewpoint or standpoint of a particular entity.
-
E.
viewingIs
Indicates that one entity is engaged in the act or state of viewing, observing, or watching 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_69d8dcffc278819086792a4ebfddfafa |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d544fef8819091147189ddd89617 |
completed | April 20, 2026, 7:27 a.m. |
| PD | Predicate disambiguation | batch_69e4a2efec5c8190840704016bf547a1 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, noon