Triple
T21257626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhou Dunyi |
E523909
|
entity |
| Predicate | placeOfDeath |
P21
|
FINISHED |
| Object | Lianxi |
—
|
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: Lianxi | Statement: [Zhou Dunyi, placeOfDeath, Lianxi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lianxi Context triple: [Zhou Dunyi, placeOfDeath, Lianxi]
-
A.
Lianjie
Lianjie is the Chinese given name of Jet Li, the internationally renowned martial artist and action film star.
-
B.
Yonglian
Yonglian was the first son and briefly designated heir of the Qianlong Emperor of the Qing dynasty, whose early death deeply affected his father and altered the imperial succession.
-
C.
Liansong
Liansong is a Chinese given name most notably borne by Zeng Liansong, the designer of the flag of the People's Republic of China.
-
D.
Lianyuan
chosen
Lianyuan is a county-level city in central Hunan Province, China, administered by the prefecture-level city of Loudi and known for its coal resources and industrial development.
-
E.
Seisyllwg
Seisyllwg was a medieval Welsh kingdom located in southwest Wales, roughly encompassing parts of modern Ceredigion and Carmarthenshire.
- 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_69e0b5146c108190adc9adb73e90abff |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e735e2f1d48190b566ab4d736fdbc4 |
completed | April 21, 2026, 8:31 a.m. |
Created at: April 16, 2026, 3:58 p.m.