Triple
T7629650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uisang |
E172726
|
entity |
| Predicate | placeOfActivity |
P1527
|
FINISHED |
| Object | Buseoksa |
E685101
|
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: Buseoksa | Statement: [Uisang, placeOfActivity, Buseoksa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Buseoksa Context triple: [Uisang, placeOfActivity, Buseoksa]
-
A.
Buseoksa
chosen
Buseoksa is a historic Korean Buddhist temple in Yeongju, renowned for its association with the monk Uisang and its well-preserved architecture and cultural heritage.
-
B.
Songgwangsa
Songgwangsa is one of Korea’s most important Zen Buddhist monasteries, renowned as a major center for monastic training and a key temple of the Jogye Order.
-
C.
Bongeunsa Temple
Bongeunsa Temple is a historic Buddhist temple in Seoul, South Korea, renowned as a tranquil spiritual retreat amid the modern skyscrapers of the Gangnam area.
-
D.
Beomeosa Temple
Beomeosa Temple is a historic Buddhist temple on the slopes of Geumjeongsan in Busan, South Korea, renowned for its scenic mountain setting, ancient halls, and cultural heritage.
-
E.
Donghaksa
Donghaksa is a historic Buddhist temple in South Korea, noted for its scenic mountain setting and traditional monastic training.
- 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_69c699517e348190bd3348b6889200f2 |
completed | March 27, 2026, 2:50 p.m. |
| NER | Named-entity recognition | batch_69c6fa84adb08190885138fc9b908ebf |
completed | March 27, 2026, 9:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8c7b3b7348190b3387dfee04fa51d |
completed | March 29, 2026, 6:33 a.m. |
Created at: March 27, 2026, 3:56 p.m.