Triple
T19376649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | He Weifang |
E484685
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | He Weifang |
—
|
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: He Weifang | Statement: [He Weifang, name, He Weifang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: He Weifang Context triple: [He Weifang, name, He Weifang]
-
A.
He Weifang
chosen
He Weifang is a prominent Chinese legal scholar and outspoken advocate for judicial independence and legal reform in China.
-
B.
He Weidong
He Weidong is a senior Chinese general who serves as one of the top leaders of China’s armed forces and a key figure in the country’s military command structure.
-
C.
Wei-Wei
Wei-Wei is a central character in Ang Lee’s film "The Wedding Banquet," a young Chinese woman who enters a marriage of convenience that becomes emotionally complicated.
-
D.
Weiwuying
Weiwuying is a major performing arts center in Kaohsiung, Taiwan, renowned for its striking contemporary architecture and large-scale cultural facilities.
-
E.
Weihui
Weihui is a county-level city in northern Henan Province, China, administered by the prefecture-level city of Xinxiang.
- 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61a5cfbf48190ac60e3ffa6baa263 |
completed | April 20, 2026, 12:21 p.m. |
Created at: April 10, 2026, 1:35 p.m.