Triple
T18916153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sky Garden |
E462728
|
entity |
| Predicate | buildingTypeOfHost |
P1844
|
FINISHED |
| Object | commercial skyscraper |
—
|
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: commercial skyscraper | Statement: [Sky Garden, buildingTypeOfHost, commercial skyscraper]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buildingTypeOfHost Context triple: [Sky Garden, buildingTypeOfHost, commercial skyscraper]
-
A.
buildingType
chosen
Indicates the specific category or function that characterizes what kind of building something is.
-
B.
hostedInBuilding
Indicates that an event, activity, or service takes place within or is accommodated inside a specific building.
-
C.
hostBuilding
Indicates that one entity serves as the building or physical structure that houses, contains, or accommodates another entity.
-
D.
intendedBuildingType
Indicates the type of building that something is planned or designed to be.
-
E.
typeOfEnterpriseBuilt
Indicates the specific kind or category of enterprise that has been constructed or established.
- 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_69d8dcfdbbb881909964fa5a75bd0b48 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c627724881909cf63c67d64321e8 |
completed | April 20, 2026, 6:22 a.m. |
| PD | Predicate disambiguation | batch_69e4a2e9e6488190ba8df92c8058ed88 |
completed | April 19, 2026, 9:39 a.m. |
Created at: April 10, 2026, 11:58 a.m.