Triple
T20454212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tripitaka Koreana |
E501732
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Haeinsa |
—
|
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: Haeinsa | Statement: [Tripitaka Koreana, locatedIn, Haeinsa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Haeinsa Context triple: [Tripitaka Koreana, locatedIn, Haeinsa]
-
A.
Haeinsa
chosen
Haeinsa is a renowned Korean Buddhist temple best known for housing the Tripitaka Koreana, the most complete extant collection of Buddhist scriptures carved onto wooden printing blocks.
-
B.
Osancheon
Osancheon is a river in Osan, South Korea, that flows through the city and serves as a local natural and recreational landmark.
-
C.
Hwangje
Hwangje is the Korean imperial title corresponding to the Chinese sovereign known as the Yellow Emperor (Huangdi).
-
D.
Yongdam Yusa
Yongdam Yusa is a key scripture of the Donghak (Eastern Learning) movement, compiling the teachings, songs, and revelations of its founder Choe Je-u.
-
E.
Hoan-ya
Hoan-ya is an alternative name for the Hoanya language, an indigenous Formosan language historically spoken in Taiwan.
- 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_69e0b4ad4940819098cf2ff6413574e5 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e68d04ca4081909b428c31d16fca10 |
completed | April 20, 2026, 8:31 p.m. |
Created at: April 16, 2026, 11:32 a.m.