Triple

T16406212
Position Surface form Disambiguated ID Type / Status
Subject Dōgen E398437 entity
Predicate studiedUnder P7251 FINISHED
Object Tiantong Rujing E940257 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: Tiantong Rujing | Statement: [Dōgen, studiedUnder, Tiantong Rujing]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tiantong Rujing
Context triple: [Dōgen, studiedUnder, Tiantong Rujing]
  • A. Yingtian
    Yingtian was an important early Ming dynasty capital city, historically centered around present-day Nanjing in China.
  • B. Tianwang Dian
    Tianwang Dian is a main entrance hall in many Chinese Buddhist temples, dedicated to the Four Heavenly Kings who protect the Dharma.
  • C. Tianjuan
    Tianjuan was a historical Chinese era name used during the reign of Emperor Taizong of the Jurchen-led Jin dynasty.
  • D. Tianhuang Daowu chosen
    Tianhuang Daowu was a prominent Chinese Chan (Zen) Buddhist monk of the Tang dynasty, known as a key successor in the Caodong/Sōtō lineage and an influential figure in classical Zen koan literature.
  • E. Tiantongyuan
    Tiantongyuan is a large residential neighborhood in northern Beijing, China, known for its dense population and extensive apartment complexes.
  • 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_69d87f2950248190bc8ad9b9bebdc8c8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e327d2b4e48190b7153f198639e9cd completed April 18, 2026, 6:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a003c62614c8190acd6d211cab1be11 completed May 10, 2026, 8:05 a.m.
Created at: April 10, 2026, 5:09 a.m.