Triple
T11673420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guiyang school |
E277433
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Yangshan Huiji |
E944100
|
NE FINISHED |
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: Yangshan Huiji | Statement: [Guiyang school, foundedBy, Yangshan Huiji]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yangshan Huiji Context triple: [Guiyang school, foundedBy, Yangshan Huiji]
-
A.
Yangshan Huiji
chosen
Yangshan Huiji was a prominent Chinese Chan (Zen) Buddhist master of the late Tang dynasty, regarded as the founder and namesake of the Guiyang school of Chan.
-
B.
Gaotangling
Gaotangling is the town that serves as the administrative seat and political center of Wangcheng County in Hunan Province, China.
-
C.
Xuefeng Yicun
Xuefeng Yicun was an influential Chinese Chan (Zen) master of the late Tang dynasty, known for helping shape the development of the Chan tradition through his teaching and disciples.
-
D.
Yishan
Yishan was a Qing dynasty military commander and noble who led Chinese forces during the First Opium War against Britain.
-
E.
Lishan Didan
Lishan Didan is a Jewish Neo-Aramaic language traditionally spoken by Kurdish and Azerbaijani Jews from the regions of northwestern Iran and eastern Turkey.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a443b6848190a1eb6825fbc49d08 |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f08fbb28548190af494ddf1a1ff986 |
completed | April 28, 2026, 10:45 a.m. |
Created at: April 8, 2026, 9:40 p.m.