Triple
T7789959
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Guangwu of Han |
E187350
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Liu Yan |
E693606
|
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: Liu Yan | Statement: [Emperor Guangwu of Han, child, Liu Yan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liu Yan Context triple: [Emperor Guangwu of Han, child, Liu Yan]
-
A.
Liu Qin
chosen
Liu Qin was a prince of the Eastern Han dynasty, known primarily as a son of Emperor Guangwu of Han.
-
B.
Lu Yanzhi
Lu Yanzhi was a Chinese architect best known for designing the monumental Sun Yat-sen Mausoleum in Nanjing.
-
C.
He Yan
He Yan was a prominent third-century Chinese philosopher and scholar-official of the Wei dynasty, best known as a leading figure of Xuanxue (Neo-Daoism) and for his influential commentarial work on the Confucian classics.
-
D.
Zhang Shouyue
Zhang Shouyue was the wife of Chinese warlord Sun Chuanfang, associated with the elite social and political circles of Republican-era China.
-
E.
Luo Peijin
Luo Peijin was a Chinese military officer and notable graduate of the Yunnan Military Academy who played a role in early 20th-century Chinese military and political affairs.
- 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_69ca82af2d2c8190963861f5e0b8bf21 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cae7ea13f08190a60c5f1863bce816 |
completed | March 30, 2026, 9:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb59f230d48190ad4cb08e9e73f19e |
completed | March 31, 2026, 5:21 a.m. |
Created at: March 30, 2026, 4:25 p.m.