Triple
T22555564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhuoshui River |
E557671
|
entity |
| Predicate | formsNaturalBoundary |
P17951
|
FINISHED |
| Object | northern Taiwan |
—
|
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: northern Taiwan | Statement: [Zhuoshui River, formsNaturalBoundary, northern Taiwan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formsNaturalBoundary Context triple: [Zhuoshui River, formsNaturalBoundary, northern Taiwan]
-
A.
formsBoundaryType
Indicates that one entity serves as a specific type of boundary for another entity.
-
B.
formsNaturalBarrierFor
Indicates that one entity physically obstructs or limits movement, access, or interaction for another entity by serving as a natural barrier.
-
C.
formsNaturalDivideBetween
chosen
Indicates that one entity serves as a natural boundary or separation between two other entities.
-
D.
formsNaturalRegionWith
Indicates that two or more geographic entities together constitute or belong to the same continuous natural region or landscape unit.
-
E.
typicalBoundary
Indicates that one entity serves as the usual or characteristic boundary or limit for another entity.
- 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_69e11e59db848190b4272ecd2b690ffd |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15f78d8288190871d54db0a7f454b |
completed | April 29, 2026, 1:31 a.m. |
| PD | Predicate disambiguation | batch_69e898cb3fb48190add6ab24a2df5822 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:52 p.m.