Triple
T5755580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yufeng Mountain |
E126957
|
entity |
| Predicate | hasNameInChinese |
P4878
|
FINISHED |
| Object | 鱼峰山 |
E126957
|
NE 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: 鱼峰山 | Statement: [Yufeng Mountain, hasNameInChinese, 鱼峰山]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 鱼峰山 Context triple: [Yufeng Mountain, hasNameInChinese, 鱼峰山]
-
A.
蛇山
蛇山 is a well-known hill in Wuhan, Hubei Province, China, noted for its scenic views over the Yangtze River and its historical and cultural significance.
-
B.
赤城山
赤城山 is a prominent volcanic mountain in Japan’s Gunma Prefecture, famed for its caldera lakes, hiking trails, and frequent appearance in Japanese folklore and popular culture.
-
C.
Xiaoguanyin Mountain
Xiaoguanyin Mountain is a prominent volcanic peak within Taiwan’s Yangmingshan range, known for its rugged terrain and scenic hiking routes.
-
D.
Yufeng Mountain
chosen
Yufeng Mountain is a scenic, historically significant mountain and popular tourist destination located near Liuzhou in China’s Guangxi region.
-
E.
象山
象山 is a popular hiking spot in Taipei, Taiwan, known for its short trail that offers panoramic views of the city skyline and Taipei 101.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c00832aedc81909899801b141fa3b4 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c02906848c8190bf7b0d62f57c27fa |
completed | March 22, 2026, 5:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c07e47c1788190b5883df385475237 |
completed | March 22, 2026, 11:41 p.m. |
Created at: March 22, 2026, 3:49 p.m.