Triple
T17749228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanghai Triad |
E443069
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Ni Zhen |
—
|
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: Ni Zhen | Statement: [Shanghai Triad, screenwriter, Ni Zhen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ni Zhen Context triple: [Shanghai Triad, screenwriter, Ni Zhen]
-
A.
Ni Zhen
chosen
Ni Zhen is a Chinese screenwriter best known for adapting Su Tong’s novella into the acclaimed film "Raise the Red Lantern," directed by Zhang Yimou.
-
B.
Zhu Zhen
Zhu Zhen was the final ruler of the Later Liang dynasty during China’s Five Dynasties and Ten Kingdoms period, whose reign ended with the dynasty’s collapse.
-
C.
Zhang Jing
Zhang Jing was a Ming dynasty Chinese official and military commander who rose to prominence as a powerful regional governor and strategist in southern China.
-
D.
Zhen Ji
Zhen Ji was a renowned noblewoman of the late Eastern Han and Three Kingdoms period, celebrated for her beauty and tragic life as a consort within the Cao Wei court.
-
E.
Zhu Zhanxi
Zhu Zhanxi was a Ming dynasty imperial prince, notable as a son of the short-reigning Hongxi Emperor of China.
- 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_69e48418c0188190beb31809b40e4648 |
completed | April 19, 2026, 7:28 a.m. |
Created at: April 10, 2026, 10:10 a.m.