Triple
T23194960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lin Zexu |
E579848
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Zexu |
—
|
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: Zexu | Statement: [Lin Zexu, givenName, Zexu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zexu Context triple: [Lin Zexu, givenName, Zexu]
-
A.
Zexu
chosen
Zexu is the given name of Lin Zexu, the prominent Qing dynasty official known for his role in suppressing the opium trade in China.
-
B.
Xiaozong
Xiaozong is the temple name of the Hongzhi Emperor, a Ming dynasty ruler noted for his relatively peaceful and reform-minded reign in late 15th-century China.
-
C.
Zejian
Zejian is the given name of Mao Zejian, a lesser-known member of the Mao family associated with Mao Zedong.
-
D.
Chi-Fu
Chi-Fu is the pompous and bureaucratic imperial advisor in Disney's 1998 animated film "Mulan," often serving as a comedic antagonist to the protagonist's efforts.
-
E.
Lin Kong
Lin Kong is an actor best known for his role in the acclaimed Chinese film "Raise the Red Lantern."
- 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_69e24600eed08190bd7e5295653a1503 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18fda64cc8190aeb5ccd8d8d20858 |
completed | April 29, 2026, 4:58 a.m. |
Created at: April 17, 2026, 4:06 p.m.