Triple
T9301313
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hilton Tower |
E223766
|
entity |
| Predicate | cantileverFeature |
P57584
|
FINISHED |
| Object | overhanging glass blade at roof level |
—
|
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: overhanging glass blade at roof level | Statement: [Hilton Tower, cantileverFeature, overhanging glass blade at roof level]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cantileverFeature Context triple: [Hilton Tower, cantileverFeature, overhanging glass blade at roof level]
-
A.
elevatedFeature
Indicates that one feature or element is positioned or raised higher relative to another reference level or surrounding context.
-
B.
designedFeature
chosen
Indicates that one entity is a feature or component intentionally planned, created, or specified by another entity as part of a design.
-
C.
tiltingCapability
Indicates the ability of one entity to tilt or be tilted relative to another or to a reference orientation.
-
D.
crestFeature
Indicates that an entity possesses a notable crest-related characteristic or structural feature.
-
E.
chamberSupportedBy
Indicates that a chamber is physically held up, carried, or structurally sustained by another object or structure.
- 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_69ca8423edb08190bc0c91287a484768 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd08d1d954819098be177addafa406 |
completed | April 1, 2026, noon |
| PD | Predicate disambiguation | batch_69cc7a5ef1908190bc5ca166bb895af6 |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:36 p.m.