Triple
T22140859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Double Fifth Festival |
E547152
|
entity |
| Predicate | commemorates |
P501
|
FINISHED |
| Object | Qu Yuan |
—
|
NE NERFINISHED |
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: Qu Yuan | Statement: [Double Fifth Festival, commemorates, Qu Yuan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Qu Yuan Context triple: [Double Fifth Festival, commemorates, Qu Yuan]
-
A.
Qu Yuan
chosen
Qu Yuan was an ancient Chinese poet and statesman of the Warring States period, renowned for his patriotic verse and associated with the origins of the Dragon Boat Festival.
-
B.
Qi Xin
Qi Xin is a Chinese revolutionary and former Party official best known as the mother of China’s paramount leader Xi Jinping.
-
C.
Liu Ban
Liu Ban was a Chinese scholar and official known for serving on the editorial team that compiled the historical chronicle Zizhi Tongjian.
-
D.
Tao Qian
Tao Qian was a late Eastern Han dynasty warlord and governor of Xu Province, best known for ceding his territory to Liu Bei before his death.
-
E.
Meng Haoran
Meng Haoran was a renowned High Tang poet celebrated for his tranquil landscape and nature-themed verse that deeply influenced classical Chinese poetry.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e3a95d88190a3bd80d9471976c3 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129beb6c8819083be3b7479bc032f |
completed | April 28, 2026, 9:42 p.m. |
Created at: April 16, 2026, 8:32 p.m.