Triple
T4459792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Police Story 2013 |
E98222
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Ding Sheng |
E470965
|
NE FINISHED |
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: Ding Sheng | Statement: [Police Story 2013, editedBy, Ding Sheng]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ding Sheng Context triple: [Police Story 2013, editedBy, Ding Sheng]
-
A.
Ding Sheng
chosen
Ding Sheng is a Chinese film director and screenwriter known for his action movies and frequent collaborations with Jackie Chan.
-
B.
Li Dongsheng
Li Dongsheng is a prominent Chinese business executive best known as the founder and chairman of the electronics company TCL Corporation.
-
C.
Liang Xiaosheng
Liang Xiaosheng is a prominent Chinese writer and scholar best known for his realist novels depicting ordinary people's lives in contemporary China.
-
D.
Zhang Ding
Zhang Ding was a prominent Chinese artist and designer best known for creating iconic national symbols of the People’s Republic of China.
-
E.
Zhu Zhanyong
Zhu Zhanyong was a Ming dynasty imperial prince, known primarily as a son of the Hongxi Emperor of China.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69b3454a7c608190944f5455c8031d73 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3567184f481908a2787e4ac9bb345 |
completed | March 13, 2026, 12:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be9c31748c81909477e01261b5a78a |
completed | March 21, 2026, 1:25 p.m. |
Created at: March 12, 2026, 11:33 p.m.