Triple
T3161332
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zijincheng |
E66107
|
entity |
| Predicate | hasChineseName |
P4878
|
FINISHED |
| Object | 紫禁城 |
E12217
|
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: 紫禁城 | Statement: [Zijincheng, hasChineseName, 紫禁城]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 紫禁城 Context triple: [Zijincheng, hasChineseName, 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.
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。
-
C.
Ming City Wall Relics Park
Ming City Wall Relics Park is a historic urban park in Beijing that preserves one of the best remaining sections of the city's Ming dynasty defensive walls and associated structures.
-
D.
Forbidden City
chosen
The Forbidden City is a vast imperial palace complex in central Beijing that served as the political and ceremonial heart of Chinese dynasties for nearly 500 years and is now a major cultural and historical museum.
-
E.
Nanjing Imperial Palace
Nanjing Imperial Palace was the primary Ming dynasty imperial residence and political center in Nanjing before the capital moved to Beijing.
- 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_69ad85850c1481908a9e9c6242238de2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada617824c8190a293230041b2f1ea |
completed | March 8, 2026, 4:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2250fa3348190b1dc2825147a2fde |
completed | March 12, 2026, 2:29 a.m. |
Created at: March 8, 2026, 3:05 p.m.