Triple
T27390356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kayan River |
E691506
|
entity |
| Predicate | flowsThroughHomelandsOf |
P128232
|
FINISHED |
| Object | Kayan people |
—
|
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: Kayan people | Statement: [Kayan River, flowsThroughHomelandsOf, Kayan people]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flowsThroughHomelandsOf Context triple: [Kayan River, flowsThroughHomelandsOf, Kayan people]
-
A.
flowsThroughTraditionalTerritoryOf
chosen
Indicates that something, typically a natural feature like a river or route, passes through the recognized traditional territory of a particular group or community.
-
B.
flowsThroughCountryRegion
Indicates that a river, stream, or similar watercourse passes through or traverses the territory of a specified country or region.
-
C.
hasHomeland
Indicates that an entity considers or recognizes a particular place or region as its homeland or place of origin.
-
D.
servesAsHomelandFor
Indicates that a place functions as the native land, origin, or primary home territory for a particular group or population.
-
E.
accessToHomeland
Indicates that an entity has the ability, right, or means to enter, return to, or be present in its homeland.
- 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_69ef520386788190bc92cfcd97ebb67a |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f6359e3d3c81909814e2f0a7fb0ea9 |
completed | May 2, 2026, 5:34 p.m. |
| PD | Predicate disambiguation | batch_69f631871c888190bf29466fe4254e51 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 12:25 p.m.