Triple
T18886531
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kangrinboqê Peak |
E461970
|
entity |
| Predicate | facesAssociatedWith |
P133679
|
FINISHED |
| Object | four cardinal directions |
—
|
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: four cardinal directions | Statement: [Kangrinboqê Peak, facesAssociatedWith, four cardinal directions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: facesAssociatedWith Context triple: [Kangrinboqê Peak, facesAssociatedWith, four cardinal directions]
-
A.
facesArea
Indicates that one entity is oriented toward, overlooks, or has its primary exposure directed toward a specified area.
-
B.
facedBy
Indicates that one entity is oriented toward and directly opposite another entity, such that it is facing it.
-
C.
facesBuilding
Indicates that one building is oriented toward and directly faces another building.
-
D.
facesCountry
Indicates that one entity is oriented toward, fronts, or directly faces the territory or border of a specified country.
-
E.
associatedWithFront
Indicates a relationship where one entity is linked or connected specifically to the front part, side, or face of another entity.
- F. None of above. chosen
Provenance (4 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_69d8dcfc3430819095ee6fc0eb4c06a5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c4760d808190b502c4ed1f24424c |
completed | April 20, 2026, 6:15 a.m. |
| PD | Predicate disambiguation | batch_69e4a2e27e1481908a8da10b28f07875 |
completed | April 19, 2026, 9:39 a.m. |
| PDg | Predicate description generation | batch_69e4afa745c081908da20a51ebc147b4 |
completed | April 19, 2026, 10:34 a.m. |
Created at: April 10, 2026, 11:58 a.m.