Triple
T13666021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yungang Grottoes |
E327121
|
entity |
| Predicate | ChineseName |
P744
|
FINISHED |
| Object | 云冈石窟 |
E327121
|
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: 云冈石窟 | Statement: [Yungang Grottoes, ChineseName, 云冈石窟]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 云冈石窟 Context triple: [Yungang Grottoes, ChineseName, 云冈石窟]
-
A.
Yungang Grottoes
chosen
Yungang Grottoes is a renowned UNESCO World Heritage site in northern China, famous for its extensive 5th–6th century Buddhist cave temples and thousands of rock-carved statues.
-
B.
白马寺
白马寺是位于中国河南省洛阳市、被誉为中国第一古刹的著名佛教寺院。
-
C.
Baodingshan site
The Baodingshan site is a major section of the Dazu Rock Carvings in Chongqing, China, renowned for its extensive and intricate Buddhist cliff sculptures and religious reliefs dating from the 12th century.
-
D.
居庸关
居庸关是位于北京西北部、长城要冲之一的著名古代关隘和军事防御要地。
-
E.
Longmen Grottoes
The Longmen Grottoes are a renowned complex of thousands of Buddhist rock carvings and statues dating from the Northern Wei and Tang dynasties, carved into limestone cliffs along the Yi River in central China.
- 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_69d8076d8270819092afc2f0e9c359a8 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc623fcc88190bbad97541c040b7a |
completed | April 12, 2026, 4:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f78b0cfe0c8190b0fe50931e9788cf |
completed | May 3, 2026, 5:51 p.m. |
Created at: April 9, 2026, 9:52 p.m.