Triple
T2909697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Moses Niagara Power Plant |
E63650
|
entity |
| Predicate | hasBuildingStructureType |
P1844
|
FINISHED |
| Object | underground power station |
—
|
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: underground power station | Statement: [Robert Moses Niagara Power Plant, hasBuildingStructureType, underground power station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBuildingStructureType Context triple: [Robert Moses Niagara Power Plant, hasBuildingStructureType, underground power station]
-
A.
hasBuildingHeightType
Indicates the classification or type used to characterize the height of a building in the relationship.
-
B.
containsBuilding
Indicates that one location or area includes a building within its boundaries.
-
C.
buildingType
chosen
Indicates the specific category or function that characterizes what kind of building something is.
-
D.
architectureType
Indicates the specific style or category of architecture that characterizes or defines an entity.
-
E.
hasBuildingFunction
Indicates that a building is used for or serves a particular function or purpose.
- 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_69ab4c44ab448190b9411324e8a1fc1d |
completed | March 6, 2026, 9:51 p.m. |
| NER | Named-entity recognition | batch_69abe0e899808190a348e1e71116d0a5 |
completed | March 7, 2026, 8:25 a.m. |
| PD | Predicate disambiguation | batch_69abdd1b77608190b20fc078fdb85e64 |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 10:11 p.m.