Triple
T17749280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Not One Less |
E443070
|
entity |
| Predicate | leadActor |
P1507
|
FINISHED |
| Object | Wei Minzhi |
—
|
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: Wei Minzhi | Statement: [Not One Less, leadActor, Wei Minzhi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wei Minzhi Context triple: [Not One Less, leadActor, Wei Minzhi]
-
A.
Wei Minzhi
chosen
Wei Minzhi is a Chinese actress best known for her breakout role as the young substitute teacher in Zhang Yimou’s film "Not One Less."
-
B.
Xi Mingze
Xi Mingze is the only daughter of Chinese leader Xi Jinping and his wife Peng Liyuan, known for maintaining a low public profile despite her prominent family background.
-
C.
Li Min
Li Min is the daughter of Chinese Communist leader Mao Zedong and his third wife He Zizhen, known primarily for her familial connection to Mao.
-
D.
Jiao Zhimin
Jiao Zhimin is a former Chinese table tennis player who won multiple medals at the 1988 Seoul Olympics and World Championships.
-
E.
Lu Yanzhi
Lu Yanzhi was a Chinese architect best known for designing the monumental Sun Yat-sen Mausoleum in Nanjing.
- 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.