Triple
T21943189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Qieyun |
E541871
|
entity |
| Predicate | compiler |
P3924
|
FINISHED |
| Object |
Lu Fayan
Lu Fayan was a Chinese scholar of the Sui dynasty best known for compiling the influential rhyme dictionary Qieyun, which became foundational for the study of Middle Chinese phonology.
|
E1511764
|
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: Lu Fayan | Statement: [Qieyun, compiler, Lu Fayan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lu Fayan Context triple: [Qieyun, compiler, Lu Fayan]
-
A.
Li Feng
Li Feng is a Chinese screenwriter best known for co-writing the acclaimed wuxia film "House of Flying Daggers."
-
B.
Li Fan
Li Fan is an actress known for her role in the acclaimed Chinese film "Not One Less," directed by Zhang Yimou.
-
C.
Yang Fengliang
Yang Fengliang is a Chinese film director best known for co-directing the acclaimed 1990 drama "Ju Dou" alongside Zhang Yimou.
-
D.
Chi Yufeng
Chi Yufeng is a Chinese entrepreneur best known as the founder of the entertainment and gaming company Perfect World Co., Ltd.
-
E.
Fu Haifeng
Fu Haifeng is a retired Chinese badminton player renowned as one of the greatest men's doubles specialists, winning multiple World Championships and Olympic gold medals.
- 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: Lu Fayan Triple: [Qieyun, compiler, Lu Fayan]
Generated description
Lu Fayan was a Chinese scholar of the Sui dynasty best known for compiling the influential rhyme dictionary Qieyun, which became foundational for the study of Middle Chinese phonology.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lu Fayan Target entity description: Lu Fayan was a Chinese scholar of the Sui dynasty best known for compiling the influential rhyme dictionary Qieyun, which became foundational for the study of Middle Chinese phonology.
-
A.
Li Feng
Li Feng is a Chinese screenwriter best known for co-writing the acclaimed wuxia film "House of Flying Daggers."
-
B.
Li Fan
Li Fan is an actress known for her role in the acclaimed Chinese film "Not One Less," directed by Zhang Yimou.
-
C.
Yang Fengliang
Yang Fengliang is a Chinese film director best known for co-directing the acclaimed 1990 drama "Ju Dou" alongside Zhang Yimou.
-
D.
Chi Yufeng
Chi Yufeng is a Chinese entrepreneur best known as the founder of the entertainment and gaming company Perfect World Co., Ltd.
-
E.
Fu Haifeng
Fu Haifeng is a retired Chinese badminton player renowned as one of the greatest men's doubles specialists, winning multiple World Championships and Olympic gold medals.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1242515ec8190b015bf8c7b13be85 |
completed | April 28, 2026, 9:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a6d6b79808190ba87aedd1ada86e3 |
completed | May 18, 2026, 1:37 a.m. |
| NEDg | Description generation | batch_6a0a6df4b3908190800df70ea35c87d5 |
completed | May 18, 2026, 1:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a6e787abc8190b192770e4d3e8daa |
completed | May 18, 2026, 1:42 a.m. |
Created at: April 16, 2026, 7:56 p.m.