Triple
T4459775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Police Story 2013 |
E98222
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Jing Tian |
E17770
|
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: Jing Tian | Statement: [Police Story 2013, starring, Jing Tian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jing Tian Context triple: [Police Story 2013, starring, Jing Tian]
-
A.
Jing Tian
chosen
Jing Tian is a Chinese actress known for her roles in both Chinese cinema and Hollywood blockbusters such as "Pacific Rim: Uprising" and "The Great Wall."
-
B.
Li Jingxi
Li Jingxi was a Chinese politician and statesman who briefly served as premier during the early years of the Republic of China.
-
C.
Jun Xia
Jun Xia is a Chinese architect best known for serving as the lead designer of Shanghai Tower, one of the world’s tallest skyscrapers.
-
D.
Lu Lingjia
Lu Lingjia is a Chinese individual known primarily as a relative of Lu Lingzi, one of the victims of the 2013 Boston Marathon bombing.
-
E.
Zhu Junyi
Zhu Junyi is a former senior Chinese police and security official best known for his involvement in major corruption scandals.
- 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_69be777f287c81909f700e22163ccc24 |
completed | March 21, 2026, 10:48 a.m. |
Created at: March 12, 2026, 11:33 p.m.