Triple
T19714130
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pingjiang Road |
E473428
|
entity |
| Predicate | runsParallelTo |
P1868
|
FINISHED |
| Object | Pingjiang 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: Pingjiang River | Statement: [Pingjiang Road, runsParallelTo, Pingjiang River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pingjiang River Context triple: [Pingjiang Road, runsParallelTo, Pingjiang River]
-
A.
Pingjiang River
chosen
Pingjiang River is a historic waterway in Suzhou, China, running through the old town’s traditional canal network and lined with ancient streets and architecture.
-
B.
Youjiang River
The Youjiang River is a major river in southwestern China that flows through Guangxi, including the city of Baise, and forms part of the upper Pearl River system.
-
C.
Nanshi River
Nanshi River is a scenic river in northern Taiwan known for its clear waters, hot springs, and role as a major natural attraction in Wulai District.
-
D.
Qingshui River
Qingshui River is a river in Xinjiang, China, that serves as a major tributary feeding water into Bosten Lake.
-
E.
Qingshui River
The Qingshui River is a tributary waterway in China that feeds into the larger Yuan River system.
- 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6440b47508190a8a33325b00841dc |
completed | April 20, 2026, 3:19 p.m. |
Created at: April 10, 2026, 1:46 p.m.