Triple
T11840780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kūkai |
E281645
|
entity |
| Predicate | honorificName |
P6819
|
FINISHED |
| Object | 弘法大師 |
E281645
|
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: 弘法大師 | Statement: [Kūkai, honorificName, 弘法大師]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 弘法大師 Context triple: [Kūkai, honorificName, 弘法大師]
-
A.
百丈懷海
百丈懷海 was an influential Tang dynasty Chan (Zen) Buddhist master known for establishing monastic regulations and emphasizing meditation in daily labor.
-
B.
Kukai
chosen
Kūkai was a Japanese Buddhist monk, scholar, poet, and calligrapher who founded the Shingon (Esoteric) school of Buddhism in Japan during the early Heian period.
-
C.
Saichō
Saichō was a Japanese Buddhist monk of the early Heian period who introduced and established the Tendai school in Japan after studying Tiantai Buddhism in China.
-
D.
Hōnen
Hōnen was a Japanese Buddhist priest who founded the Jōdo-shū (Pure Land) school and popularized exclusive nembutsu practice as the primary path to salvation.
-
E.
洞山良价
洞山良价 was a prominent 9th-century Chinese Chan (Zen) master, co-founder of the Caodong (Sōtō) school, known for his subtle teachings on nonduality and the “Five Ranks.”
- 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_69d6ab276f8c8190b1966a0ef11349ac |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a658f918819092c2db05fe2ab0ce |
completed | April 10, 2026, 7:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f1678668ac81909bddf67e8c176757 |
completed | April 29, 2026, 2:05 a.m. |
Created at: April 8, 2026, 9:43 p.m.