Triple
T22008583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 归来 |
E543513
|
entity |
| Predicate | leadActress |
P6108
|
FINISHED |
| Object | 巩俐 |
—
|
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: 巩俐 | Statement: [归来, leadActress, 巩俐]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 巩俐 Context triple: [归来, leadActress, 巩俐]
-
A.
Gong Li
chosen
Gong Li is a renowned Chinese actress acclaimed for her powerful performances in films by directors such as Zhang Yimou and Chen Kaige, and for helping bring Chinese cinema to international prominence.
-
B.
Zhang Ziyi
Zhang Ziyi is a renowned Chinese actress known internationally for her roles in films such as "Crouching Tiger, Hidden Dragon," "Hero," and "Memoirs of a Geisha."
-
C.
Tang Wei
Tang Wei is a Chinese actress best known internationally for her breakout leading role in Ang Lee’s espionage thriller film "Lust, Caution."
-
D.
Li Bingbing
Li Bingbing is a Chinese actress known internationally for her roles in both Chinese cinema and Hollywood films, including action and science fiction blockbusters.
-
E.
Zhao Tao
Zhao Tao is a renowned Chinese actress best known for her long-term collaboration with director Jia Zhangke in critically acclaimed art-house films.
- 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_69e11e2db934819095556760c7d85e4d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127a2aebc8190951ee0bf9fd8e16d |
completed | April 28, 2026, 9:33 p.m. |
Created at: April 16, 2026, 8:21 p.m.