Triple
T24044789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arizona–Utah border |
E595486
|
entity |
| Predicate | crossesReservoir |
P15424
|
FINISHED |
| Object | Lake Powell |
—
|
NE NERFINISHED |
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: Lake Powell | Statement: [Arizona–Utah border, crossesReservoir, Lake Powell]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crossesReservoir Context triple: [Arizona–Utah border, crossesReservoir, Lake Powell]
-
A.
crossesWatershed
Indicates that one entity passes from one drainage basin or watershed area into another, traversing the boundary between them.
-
B.
crossedByRiver
Indicates that a river passes across or through a specified area, feature, or route.
-
C.
waterwayTypeCrossed
Indicates the specific kind of waterway (e.g., river, canal, stream) that is being crossed in the described relationship or action.
-
D.
crossingOf
Indicates that one entity serves as the intersection or crossing point of two or more linear features, such as roads, paths, or tracks.
-
E.
crossesWaterBody
chosen
Indicates that an entity moves from one side of a water body to the other by passing over, through, or across it.
- 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_69e288c06a908190899cad4531f32c9a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d8dc8f708190ac6257e65c37bde7 |
completed | April 29, 2026, 10:09 a.m. |
| PD | Predicate disambiguation | batch_69f1764345388190a3102b62ddb729b4 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 10:11 p.m.