Triple
T17749030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ju Dou |
E443065
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object |
Fuxi Fuxi
Fuxi Fuxi is a literary work that served as the source material for the Chinese film "Ju Dou."
|
E1285125
|
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: Fuxi Fuxi | Statement: [Ju Dou, basedOn, Fuxi Fuxi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fuxi Fuxi Context triple: [Ju Dou, basedOn, Fuxi Fuxi]
-
A.
Taiyu
Taiyu is a Southern Min (Hokkien) Chinese language variety widely spoken in Taiwan and by overseas Chinese communities.
-
B.
Yu the Great
Yu the Great is a legendary Chinese ruler famed for controlling the Great Flood and founding the Xia dynasty, traditionally regarded as China’s first dynasty.
-
C.
Huangdi
Huangdi is the Chinese term for "emperor," denoting the supreme sovereign of imperial China.
-
D.
Xiaojing Huangdi
Xiaojing Huangdi is the posthumous temple name of Emperor Jing of Han, a Western Han dynasty ruler known for consolidating imperial power and promoting economic stability in ancient China.
-
E.
Zhuanxu
Zhuanxu is a legendary ancient Chinese emperor and cultural hero, traditionally regarded as one of the Five Emperors and an important ancestral figure in early Chinese myth and royal genealogies.
- 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: Fuxi Fuxi Triple: [Ju Dou, basedOn, Fuxi Fuxi]
Generated description
Fuxi Fuxi is a literary work that served as the source material for the Chinese film "Ju Dou."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Fuxi Fuxi Target entity description: Fuxi Fuxi is a literary work that served as the source material for the Chinese film "Ju Dou."
-
A.
Taiyu
Taiyu is a Southern Min (Hokkien) Chinese language variety widely spoken in Taiwan and by overseas Chinese communities.
-
B.
Yu the Great
Yu the Great is a legendary Chinese ruler famed for controlling the Great Flood and founding the Xia dynasty, traditionally regarded as China’s first dynasty.
-
C.
Huangdi
Huangdi is the Chinese term for "emperor," denoting the supreme sovereign of imperial China.
-
D.
Xiaojing Huangdi
Xiaojing Huangdi is the posthumous temple name of Emperor Jing of Han, a Western Han dynasty ruler known for consolidating imperial power and promoting economic stability in ancient China.
-
E.
Zhuanxu
Zhuanxu is a legendary ancient Chinese emperor and cultural hero, traditionally regarded as one of the Five Emperors and an important ancestral figure in early Chinese myth and royal genealogies.
- 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e47ad46a50819089c87f74efe3c7ca |
completed | April 19, 2026, 6:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a024304d6cc819097666c7f3fd2fd07 |
completed | May 11, 2026, 8:58 p.m. |
| NEDg | Description generation | batch_6a02458aaac88190b62258e1983100f4 |
completed | May 11, 2026, 9:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a02462830088190b036cca2840c287c |
completed | May 11, 2026, 9:12 p.m. |
Created at: April 10, 2026, 10:10 a.m.