Triple
T8903308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Emei |
E211984
|
entity |
| Predicate | ChineseName |
P744
|
FINISHED |
| Object | 峨眉山 |
E211984
|
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: 峨眉山 | Statement: [Mount Emei, ChineseName, 峨眉山]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 峨眉山 Context triple: [Mount Emei, ChineseName, 峨眉山]
-
A.
武当山
武当山是位于中国湖北省的著名道教名山和世界文化遗产，以其古建筑群和武当武术而闻名。
-
B.
Mount Emei
chosen
Mount Emei is one of China’s Four Sacred Buddhist Mountains, renowned for its ancient temples, rich biodiversity, and dramatic, cloud-wreathed peaks.
-
C.
长白山
长白山是一座位于中朝边界、以火山天池和丰富自然资源闻名的著名高山与风景名胜区。
-
D.
Mount Qingcheng
Mount Qingcheng is a renowned Taoist sacred mountain in Sichuan, China, celebrated for its lush forested peaks, ancient temples, and tranquil spiritual atmosphere.
-
E.
Mount Emei Scenic Area including Leshan Giant Buddha
Mount Emei Scenic Area including Leshan Giant Buddha is a renowned cultural and natural site in China, famous for its sacred Buddhist mountain landscapes and the colossal stone Buddha statue carved into a cliff face.
- 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_69ca839255248190b43984294abd92ae |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc64c091d08190b59e54eb4a184e41 |
completed | April 1, 2026, 12:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfba26bc7881908639e9a812dec894 |
completed | April 3, 2026, 1:01 p.m. |
Created at: March 30, 2026, 6:55 p.m.