Triple
T32345989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bel-Air metro station |
E826460
|
entity |
| Predicate | hasPlatformDecoration |
P38145
|
FINISHED |
| Object | standard white-tiled vault |
—
|
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: standard white-tiled vault | Statement: [Bel-Air metro station, hasPlatformDecoration, standard white-tiled vault]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPlatformDecoration Context triple: [Bel-Air metro station, hasPlatformDecoration, standard white-tiled vault]
-
A.
hasDecor
chosen
Indicates that one entity possesses, features, or is adorned with a particular decorative element or style.
-
B.
containsDecorationFrom
Indicates that one entity includes or incorporates a decorative element that originates from another entity.
-
C.
hasDeepPlatform
Indicates that one entity possesses or provides a platform characterized by significant depth, capability, or extensiveness in supporting another entity’s activities or functions.
-
D.
hasPlatformType
Indicates that an entity is associated with or characterized by a specific type or category of platform.
-
E.
hasPlatformEdge
Indicates that an entity possesses or includes a boundary or edge associated with a platform.
- 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_69f34914dfc48190a390cd0720d9e86f |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fcc7338120819081cb46547d60f2cb |
completed | May 7, 2026, 5:09 p.m. |
| PD | Predicate disambiguation | batch_69fcc58566a0819082d5ea36e03bf0c6 |
completed | May 7, 2026, 5:01 p.m. |
Created at: May 1, 2026, 12:48 a.m.