Triple
T13872520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wu Jing |
E333489
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | 吴京 |
E333489
|
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: 吴京 | Statement: [Wu Jing, nativeName, 吴京]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 吴京 Context triple: [Wu Jing, nativeName, 吴京]
-
A.
Wu Jing
chosen
Wu Jing is a Chinese actor, director, and martial artist best known internationally for directing and starring in the blockbuster action films "Wolf Warrior" and "Wolf Warrior 2."
-
B.
Haifan Lin
Haifan Lin is a prominent stem cell and developmental biologist known for his pioneering research on germline stem cells and RNA regulation.
-
C.
Chang Chen
Chang Chen is a Taiwanese actor known for his roles in acclaimed films such as "Crouching Tiger, Hidden Dragon," "Happy Together," and various international productions.
-
D.
Lu Jun
Lu Jun is a family member of Lu Lingzi, the Chinese graduate student who was killed in the 2013 Boston Marathon bombing.
-
E.
Chen Zilong
Chen Zilong was a late Ming dynasty Chinese poet and scholar known for his refined lyrical style and loyalist stance during the dynasty’s collapse.
- 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_69d81c5ced9c8190b0e9bcc6effe5959 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de05c638248190bbe5d19f7b88d0f9 |
completed | April 14, 2026, 9:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c107c20c81909dff0ca4a59fcc55 |
completed | May 3, 2026, 9:41 p.m. |
Created at: April 9, 2026, 10:14 p.m.