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.