Triple
T13823375
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zǐjìnchéng |
E332189
|
entity |
| Predicate | pinyinTransliterationOf |
P41219
|
FINISHED |
| Object |
紫禁城
紫禁城是位于中国北京、明清两代皇帝居住和处理政务的皇家宫殿建筑群,也是世界上现存规模最大、保存最完整的古代宫殿之一。
|
E815749
|
NE FINISHED |
How this triple was built (5 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: 紫禁城 | Statement: [Zǐjìnchéng, pinyinTransliterationOf, 紫禁城]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 紫禁城 Context triple: [Zǐjìnchéng, pinyinTransliterationOf, 紫禁城]
-
A.
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。
-
B.
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。
-
C.
午门
午门 is the grand southern entrance and main gate of Beijing’s Forbidden City, historically used for important imperial ceremonies and proclamations.
-
D.
北京皇城
北京皇城是明清两代北京城中围绕皇宫设置的内城区域,汇集重要宫殿、坛庙和皇家建筑群的核心防御与礼制空间。
-
E.
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。
- 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: 紫禁城 Triple: [Zǐjìnchéng, pinyinTransliterationOf, 紫禁城]
Generated description
紫禁城是位于中国北京、明清两代皇帝居住和处理政务的皇家宫殿建筑群,也是世界上现存规模最大、保存最完整的古代宫殿之一。
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 紫禁城 Target entity description: 紫禁城是位于中国北京、明清两代皇帝居住和处理政务的皇家宫殿建筑群,也是世界上现存规模最大、保存最完整的古代宫殿之一。
-
A.
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。
-
B.
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。
-
C.
午门
午门 is the grand southern entrance and main gate of Beijing’s Forbidden City, historically used for important imperial ceremonies and proclamations.
-
D.
北京皇城
chosen
北京皇城是明清两代北京城中围绕皇宫设置的内城区域,汇集重要宫殿、坛庙和皇家建筑群的核心防御与礼制空间。
-
E.
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。
- F. None of above.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pinyinTransliterationOf Context triple: [Zǐjìnchéng, pinyinTransliterationOf, 紫禁城]
-
A.
ChinesePinyin
chosen
Indicates that one entity is the Chinese pinyin (romanized phonetic transcription) representation of another entity.
-
B.
transliterationName
Indicates that one entity is the transliterated form of another entity’s name from one writing system into another.
-
C.
formerTransliteration
Indicates that one transliteration was previously used for an entity but has since been replaced by a different transliteration.
-
D.
transliterationTarget
Indicates that one entity is the target script or form into which another entity is transliterated.
-
E.
standardTransliteration
Indicates that one representation of text is a transliteration of another according to a recognized standard or convention.
- F. None of above.
Provenance (6 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_69d81c5ae7c88190b0dd41bdafeb5999 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0285fb7c8190be4b90bdc0d6fa53 |
completed | April 14, 2026, 9:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b8e60e1c81908d51d723e85e0541 |
completed | May 3, 2026, 9:06 p.m. |
| NEDg | Description generation | batch_69f7b9d81f488190875e9b3f885556ab |
completed | May 3, 2026, 9:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f7ba9ba0988190800e685cff4c2186 |
completed | May 3, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69dbc86668e08190ba9135d1c3f38d35 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:13 p.m.