Triple
T17025856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pedicab Driver |
E413060
|
entity |
| Predicate | screenplayBy |
P15305
|
FINISHED |
| Object |
Yuen Kai‑chi
Yuen Kai‑chi is a Hong Kong screenwriter best known for his work on action and comedy films.
|
E1271387
|
NE FINISHED |
How this triple was built (4 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: Yuen Kai‑chi | Statement: [Pedicab Driver, screenplayBy, Yuen Kai‑chi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yuen Kai‑chi Context triple: [Pedicab Driver, screenplayBy, Yuen Kai‑chi]
-
A.
Chow Chi-yuen
Chow Chi-yuen is a person bearing the Chinese surname Chow, about whom only limited public information is readily available.
-
B.
Kwok Yuen Ho
Kwok Yuen Ho is a technology entrepreneur best known as the co-founder and early leader of ATI Technologies, a pioneering company in the graphics processing industry.
-
C.
Chow Kwok-ching
Chow Kwok-ching is an individual notable enough to be specifically cited as a bearer of the surname Chow, though detailed public information about their life or achievements is limited.
-
D.
Cheng Siu-Keung
Cheng Siu-Keung is a Hong Kong cinematographer best known for his frequent collaborations with director Johnnie To on numerous acclaimed crime and action films.
-
E.
Chow Kwok-yan
Chow Kwok-yan is a person notable enough to be specifically distinguished among individuals with the surname Chow.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Yuen Kai‑chi Triple: [Pedicab Driver, screenplayBy, Yuen Kai‑chi]
Generated description
Yuen Kai‑chi is a Hong Kong screenwriter best known for his work on action and comedy films.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Yuen Kai‑chi Target entity description: Yuen Kai‑chi is a Hong Kong screenwriter best known for his work on action and comedy films.
-
A.
Chow Chi-yuen
Chow Chi-yuen is a person bearing the Chinese surname Chow, about whom only limited public information is readily available.
-
B.
Kwok Yuen Ho
Kwok Yuen Ho is a technology entrepreneur best known as the co-founder and early leader of ATI Technologies, a pioneering company in the graphics processing industry.
-
C.
Chow Kwok-ching
Chow Kwok-ching is an individual notable enough to be specifically cited as a bearer of the surname Chow, though detailed public information about their life or achievements is limited.
-
D.
Cheng Siu-Keung
Cheng Siu-Keung is a Hong Kong cinematographer best known for his frequent collaborations with director Johnnie To on numerous acclaimed crime and action films.
-
E.
Chow Kwok-yan
Chow Kwok-yan is a person notable enough to be specifically distinguished among individuals with the surname Chow.
- F. None of above. chosen
Provenance (5 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_69d886cc4170819093deddc7b8b4b6a7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d5d46a5081908bc5681621dd8534 |
completed | April 18, 2026, 7:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01c1e589e081908b12287aa3b05bb6 |
completed | May 11, 2026, 11:47 a.m. |
| NEDg | Description generation | batch_6a01c2c7e32c8190a17307722f5eb50d |
completed | May 11, 2026, 11:51 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a01c33ec9c0819081f7ab7cd8c0eb42 |
completed | May 11, 2026, 11:53 a.m. |
Created at: April 10, 2026, 5:33 a.m.