Triple
T22310309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baishan |
E551492
|
entity |
| Predicate | river |
P165
|
FINISHED |
| Object | Yalu River |
—
|
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: Yalu River | Statement: [Baishan, river, Yalu River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yalu River Context triple: [Baishan, river, Yalu River]
-
A.
Yalu River
chosen
The Yalu River is a major East Asian river that forms much of the border between North Korea and China and has long held strategic and historical significance in the region.
-
B.
Tumen-gang River
Tumen-gang River is a border river in Northeast Asia that flows between China, North Korea, and Russia before emptying into the Sea of Japan.
-
C.
Changjin River
The Changjin River is a river in northeastern North Korea known for flowing through the mountainous region near the Chosin Reservoir, a key site in the Korean War.
-
D.
Ch'ongch'on River
The Ch'ongch'on River is a major river in northwestern North Korea that gained historical significance as the site of a pivotal battle during the Korean War.
-
E.
Yi River
The Yi River is a significant river in Shandong Province, China, known for flowing through the city of Linyi and its surrounding agricultural and historical regions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e46c0188190800181a4233f28fe |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1574d53148190a1ec07f849e1ae9d |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:42 p.m.