Triple
T12345760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liao Zhongkai |
E294349
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Liao |
E958343
|
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: Liao | Statement: [Liao Zhongkai, familyName, Liao]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liao Context triple: [Liao Zhongkai, familyName, Liao]
-
A.
Liao
chosen
Liao is a surname of Chinese origin borne by various notable individuals across fields such as acting, politics, and academia.
-
B.
Luoyi
Luoyi was an ancient Chinese city that served as a major political and cultural center of the Zhou dynasty.
-
C.
Ronglu
Ronglu was a high-ranking Qing dynasty general and statesman who played a key role in military and political affairs during the late imperial period, including the Boxer Rebellion.
-
D.
Liang
Liang is a common Chinese surname borne by numerous historical figures, scholars, and public personalities across the Chinese-speaking world.
-
E.
Hui
The Hui are a predominantly Muslim ethnic group in China known for their integration of Islamic faith with Han Chinese language and cultural practices.
- 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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f7a4a448190aa70d66dc2f406c1 |
completed | April 10, 2026, 6:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f62aac9edc8190ab1740d23af1b250 |
completed | May 2, 2026, 4:47 p.m. |
Created at: April 8, 2026, 9:53 p.m.