Triple
T31976339
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 澜沧江 |
E816457
|
entity |
| Predicate | 跨境性质 |
P95603
|
FINISHED |
| Object | 国际河流 |
—
|
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: 国际河流 | Statement: [澜沧江, 跨境性质, 国际河流]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 跨境性质 Context triple: [澜沧江, 跨境性质, 国际河流]
-
A.
isCrossBorder
chosen
Indicates that the relationship or action involves entities located in or spanning across different national or jurisdictional boundaries.
-
B.
hasCrossBorderTrade
Indicates that there is trade or commercial exchange occurring between entities located in different countries or jurisdictions.
-
C.
haveMajorCrossBorderOrganization
Indicates that an entity possesses or is associated with a significant organization that operates across national borders.
-
D.
crossBorderTradeHub
Indicates a location or entity that serves as a central point for facilitating, coordinating, or processing trade activities that occur across national or regional borders.
-
E.
hasCrossBorderInteraction
Indicates that there is an interaction, activity, or relationship occurring between entities located in different countries or jurisdictions.
- 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_69f348f6a3008190bfb59ca695fd68e2 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b344b24881908bf1da55fd9b3a97 |
completed | May 3, 2026, 2:30 a.m. |
| PD | Predicate disambiguation | batch_69f6b151ad008190836c1bcdec503ce2 |
completed | May 3, 2026, 2:22 a.m. |
Created at: May 1, 2026, 12:11 a.m.