Triple
T15296648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanghai Noon |
E365677
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Roger Yuan |
E380853
|
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: Roger Yuan | Statement: [Shanghai Noon, starring, Roger Yuan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roger Yuan Context triple: [Shanghai Noon, starring, Roger Yuan]
-
A.
Roger Yuan
chosen
Roger Yuan is an American martial artist, fight choreographer, and actor known for his roles and stunt work in numerous action films.
-
B.
Ted Hsu
Ted Hsu is a Taiwanese entrepreneur best known as one of the co-founders of the technology company ASUS.
-
C.
Jimmy Liu
Jimmy Liu is an actor best known for his role in the television adaptation of the graphic novel "American Born Chinese."
-
D.
Luke Chia-Liu Yuan
Luke Chia-Liu Yuan was a Chinese-American physicist and engineer known for his work in nuclear physics and for being part of a prominent scientific family that included his wife, experimental physicist Chien-Shiung Wu.
-
E.
Jerry Chen
Jerry Chen is a prominent venture capitalist and general partner at Greylock Partners, known for investing in enterprise software and infrastructure startups.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e036848c1881908fbaaae0216d6d27 |
completed | April 16, 2026, 1:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff0b3b8a8c81908aa936613565b87a |
completed | May 9, 2026, 10:23 a.m. |
Created at: April 10, 2026, 3:15 a.m.