Triple
T16919113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 排云殿 |
E410395
|
entity |
| Predicate | 管理机构 |
P9686
|
FINISHED |
| Object |
北京市颐和园管理处
北京市颐和园管理处是负责北京颐和园景区文物保护、园林维护与日常运营管理的行政管理机构。
|
E1243799
|
NE FINISHED |
How this triple was built (4 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: 北京市颐和园管理处 | Statement: [排云殿, 管理机构, 北京市颐和园管理处]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 北京市颐和园管理处 Context triple: [排云殿, 管理机构, 北京市颐和园管理处]
-
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.
Beijing Municipal Administration of Parks
The Beijing Municipal Administration of Parks is the city-level government agency responsible for overseeing, maintaining, and operating Beijing’s public parks and major historical gardens.
-
C.
北海公园
北海公园是位于北京市中心、以皇家园林景观和历史文化遗迹著称的大型古典园林公园。
-
D.
Beijing Municipal Ecology and Environment Bureau
The Beijing Municipal Ecology and Environment Bureau is the city-level government agency responsible for formulating and enforcing environmental protection and ecological conservation policies in Beijing.
-
E.
Haidian District Government
Haidian District Government is the administrative authority responsible for governing Beijing’s Haidian District, including areas such as Qinghe Subdistrict.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: 北京市颐和园管理处 Triple: [排云殿, 管理机构, 北京市颐和园管理处]
Generated description
北京市颐和园管理处是负责北京颐和园景区文物保护、园林维护与日常运营管理的行政管理机构。
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 北京市颐和园管理处 Target entity description: 北京市颐和园管理处是负责北京颐和园景区文物保护、园林维护与日常运营管理的行政管理机构。
-
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.
Beijing Municipal Administration of Parks
The Beijing Municipal Administration of Parks is the city-level government agency responsible for overseeing, maintaining, and operating Beijing’s public parks and major historical gardens.
-
C.
北海公园
北海公园是位于北京市中心、以皇家园林景观和历史文化遗迹著称的大型古典园林公园。
-
D.
Beijing Municipal Ecology and Environment Bureau
The Beijing Municipal Ecology and Environment Bureau is the city-level government agency responsible for formulating and enforcing environmental protection and ecological conservation policies in Beijing.
-
E.
Haidian District Government
Haidian District Government is the administrative authority responsible for governing Beijing’s Haidian District, including areas such as Qinghe Subdistrict.
- F. None of above. chosen
Provenance (5 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_69d886c7b1e481908c3766dfa8c13458 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cdec3d0c8190994a0fca335c65d6 |
completed | April 18, 2026, 6:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00d45a6ee8819092ae7c572be68e62 |
completed | May 10, 2026, 6:54 p.m. |
| NEDg | Description generation | batch_6a00d579f2a88190ad49cd451f4c27cd |
completed | May 10, 2026, 6:59 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00d940b5c4819080759f6d974067b8 |
completed | May 10, 2026, 7:15 p.m. |
Created at: April 10, 2026, 5:30 a.m.