Triple
T20170378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snow Town (China Snow Town) |
E491942
|
entity |
| Predicate | ChineseName |
P744
|
FINISHED |
| Object | 中国雪乡 |
—
|
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: 中国雪乡 | Statement: [Snow Town (China Snow Town), ChineseName, 中国雪乡]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 中国雪乡 Context triple: [Snow Town (China Snow Town), ChineseName, 中国雪乡]
-
A.
Snow Town (China Snow Town)
chosen
Snow Town (China Snow Town) is a famous winter resort village in Heilongjiang, China, renowned for its heavy snowfall, picturesque snow-covered landscapes, and traditional wooden houses.
-
B.
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。
-
C.
白山
白山は、東京都文京区に位置する住宅街と商業施設が混在した落ち着いた街並みのエリアです。
-
D.
Jilin rime ice scenery
Jilin rime ice scenery is a famous winter landscape along the Songhua River in Jilin Province, China, renowned for its spectacular frost-covered trees and ethereal icy vistas.
-
E.
Harbin Polarland
Harbin Polarland is a popular polar-themed amusement and marine life park in Harbin, China, known for its Arctic and Antarctic animal exhibits and ice-related attractions.
- 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66847ed9481908e6b23b399fa7005 |
completed | April 20, 2026, 5:54 p.m. |
Created at: April 11, 2026, 11:35 p.m.