Triple
T23519394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Western Capital |
E574460
|
entity |
| Predicate | transliterationOf |
P5923
|
FINISHED |
| Object | Xijing |
—
|
NE NERFINISHED |
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: Xijing | Statement: [Western Capital, transliterationOf, Xijing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Xijing Context triple: [Western Capital, transliterationOf, Xijing]
-
A.
Xijing
chosen
Xijing is the historical name of Xi'an, one of China’s oldest and most important ancient capitals.
-
B.
Pizhou
Pizhou is a county-level city administered by Xuzhou in Jiangsu Province, eastern China, known for its historical sites and regional commerce.
-
C.
Changling
Changling is the largest and best-preserved mausoleum within Beijing’s Ming Tombs complex, built for the Yongle Emperor and his empress.
-
D.
Daliang
Daliang was the principal city and political center of the ancient Chinese State of Wei during the Warring States period.
-
E.
Xishan
Xishan is the given name of Yan Xishan, a prominent Chinese warlord and political leader active in Shanxi during the early 20th century.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245bb3dcc8190ba9a2b35972b58d0 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1aa84fe7c8190aa1078a118af7d61 |
completed | April 29, 2026, 6:51 a.m. |
Created at: April 17, 2026, 6:08 p.m.