Triple
T22210173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leehom Wang |
E548920
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Lee Jinglei |
—
|
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: Lee Jinglei | Statement: [Leehom Wang, spouse, Lee Jinglei]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lee Jinglei Context triple: [Leehom Wang, spouse, Lee Jinglei]
-
A.
Xu Jinglei
chosen
Xu Jinglei is a prominent Chinese actress and film director known for her influential work in contemporary Chinese cinema and her early success as part of the "Four Dan Actresses" of China.
-
B.
Kong Jinlei
Kong Jinlei is an editor known for working on the publication or project titled "Platform."
-
C.
Li Liejun
Li Liejun was a Chinese revolutionary and military leader who played a significant role in the overthrow of the Qing dynasty and the early years of the Republic of China.
-
D.
Li Jiong
Li Jiong was a Tang dynasty imperial prince, known primarily as a son of Emperor Xianzong of Tang.
-
E.
Li Qiang
Li Qiang is a Chinese politician serving as the premier of the People's Republic of China and a close ally of President Xi Jinping.
- 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_69e11e3f7e04819089806d81d5ac431e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12b2aefb881909bddbabd4be0bd58 |
completed | April 28, 2026, 9:48 p.m. |
Created at: April 16, 2026, 8:36 p.m.