Triple
T17749026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ju Dou |
E443065
|
entity |
| Predicate | coDirector |
P17194
|
FINISHED |
| Object | Yang Fengliang |
—
|
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: Yang Fengliang | Statement: [Ju Dou, coDirector, Yang Fengliang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yang Fengliang Context triple: [Ju Dou, coDirector, Yang Fengliang]
-
A.
Yang Fengliang
chosen
Yang Fengliang is a Chinese film director best known for co-directing the acclaimed 1990 drama "Ju Dou" alongside Zhang Yimou.
-
B.
Yang Fenggang
Yang Fenggang is a prominent sociologist of religion known for his influential research on Christianity and religious change in contemporary China.
-
C.
Yu Fengzhi
Yu Fengzhi was a Chinese educator and social activist best known as the wife of warlord Zhang Xueliang and for her later work promoting Chinese culture and education abroad.
-
D.
Wu Jingyu
Wu Jingyu is a Chinese taekwondo athlete and multiple-time Olympic gold medalist renowned as one of the sport’s most successful competitors.
-
E.
Zhang Lingfu
Zhang Lingfu was a prominent Nationalist Chinese general during the Chinese Civil War, noted for his leadership in several key campaigns and his eventual death in battle.
- 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e47ad46a50819089c87f74efe3c7ca |
completed | April 19, 2026, 6:48 a.m. |
Created at: April 10, 2026, 10:10 a.m.