Triple
T24044759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arizona–Utah border |
E595486
|
entity |
| Predicate | passesThroughAttraction |
P34612
|
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, passesThroughAttraction, Lake Powell]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: passesThroughAttraction Context triple: [Arizona–Utah border, passesThroughAttraction, Lake Powell]
-
A.
passesThroughPark
Indicates that the path, route, or movement of an entity goes through or crosses a park as part of its course.
-
B.
passesThroughArea
chosen
Indicates that an entity moves or extends through the spatial region defined by another entity or area.
-
C.
succeededByAttraction
Indicates that one attraction or point of interest is directly followed or replaced by another attraction in a sequence or timeline.
-
D.
passesUnder
Indicates that one entity moves or extends beneath another entity, typically crossing below it without direct contact.
-
E.
passesThroughFacility
Indicates that something (such as a person, object, or shipment) moves through or is routed via a particular facility as part of its path or process.
- 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.