Triple
T6791674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Heng (Hengshan, Hunan) |
E155945
|
entity |
| Predicate | chineseName |
P4878
|
FINISHED |
| Object | 衡山 |
E155945
|
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: 衡山 | Statement: [Mount Heng (Hengshan, Hunan), chineseName, 衡山]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 衡山 Context triple: [Mount Heng (Hengshan, Hunan), chineseName, 衡山]
-
A.
Mount Heng (Hengshan, Hunan)
chosen
Mount Heng (Hengshan, Hunan) is one of China’s Five Great Mountains, renowned as a sacred center of Taoist worship and a historic site of temples and pilgrimage in Hunan Province.
-
B.
Yuelu Mountain
Yuelu Mountain is a scenic and historic mountain area in Changsha, China, known for its ancient academy, temples, and natural landscapes.
-
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.
Wuling Mountain
Wuling Mountain is a prominent peak in northern China known as the highest summit of the Yan Mountains range.
-
E.
Xiaowutai Mountain
Xiaowutai Mountain is the highest peak of the Taihang mountain range in northern China, known for its rugged terrain and alpine scenery.
- 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_69c6881770fc8190972b2906390380f5 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d2ae4d1c819089ac6b3abf11a341 |
completed | March 27, 2026, 6:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c71a8eaefc819098e848b3012da749 |
completed | March 28, 2026, 12:02 a.m. |
Created at: March 27, 2026, 2:15 p.m.