Triple
T3374582
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chengde Mountain Resort |
E71035
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | 承德避暑山庄 |
E71035
|
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: 承德避暑山庄 | Statement: [Chengde Mountain Resort, nativeName, 承德避暑山庄]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 承德避暑山庄 Context triple: [Chengde Mountain Resort, nativeName, 承德避暑山庄]
-
A.
颐和园
颐和园是位于北京市西北部、以宏伟的皇家园林建筑和昆明湖、万寿山自然景观著称的世界文化遗产。
-
B.
Chengde Mountain Resort
chosen
Chengde Mountain Resort is a vast Qing dynasty imperial summer palace and landscaped garden complex in northern China, renowned for its blend of Chinese and foreign architectural styles and its status as a UNESCO World Heritage Site.
-
C.
太庙
太庙是北京故宫东侧一座明清皇家宗庙建筑群，现为对公众开放的历史文化景区。
-
D.
保和殿
保和殿 is one of the principal ceremonial halls within Beijing’s Forbidden City, historically used for imperial banquets and important state rituals.
-
E.
天安门
天安门是位于北京市中心、作为中国象征性地标和重要政治历史事件发生地的著名城门与广场名称。
- 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_69ad85a7f80c8190a05e43013f298942 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2bf4ad88190a2c49dc30f323a13 |
completed | March 8, 2026, 5:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b33442f28c8190b48a662a5dd1bac3 |
completed | March 12, 2026, 9:46 p.m. |
Created at: March 8, 2026, 3:13 p.m.