Triple
T23216844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eunpyeong-gu |
E580767
|
entity |
| Predicate | hasTemple |
P1191
|
FINISHED |
| Object |
Bulgwangsa
Bulgwangsa is a Buddhist temple located in the Eunpyeong-gu district of Seoul, South Korea.
|
E1576197
|
NE FINISHED |
How this triple was built (4 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: Bulgwangsa | Statement: [Eunpyeong-gu, hasTemple, Bulgwangsa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bulgwangsa Context triple: [Eunpyeong-gu, hasTemple, Bulgwangsa]
-
A.
Daejonggyo
Daejonggyo is a modern Korean ethnic religion that venerates the legendary founder Dangun as a divine ancestor and centers on Korean national identity and spiritual heritage.
-
B.
Hanguk Suhwagi
Hanguk Suhwagi is the Korean Sign Language used by the Deaf community in South Korea for everyday communication and cultural expression.
-
C.
Gwanse-eum
Gwanse-eum is the Korean name for Avalokiteśvara, the bodhisattva of compassion revered in Mahayana Buddhism.
-
D.
Geunchogo-wang
Geunchogo-wang was a prominent 4th-century king of the Korean kingdom of Baekje, known for greatly expanding its territory and strengthening its cultural and political influence.
-
E.
Sokdaejeon
Sokdaejeon was an earlier Joseon Dynasty legal code that laid the groundwork for the later, more comprehensive Gyeongguk Daejeon.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Bulgwangsa Triple: [Eunpyeong-gu, hasTemple, Bulgwangsa]
Generated description
Bulgwangsa is a Buddhist temple located in the Eunpyeong-gu district of Seoul, South Korea.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bulgwangsa Target entity description: Bulgwangsa is a Buddhist temple located in the Eunpyeong-gu district of Seoul, South Korea.
-
A.
Daejonggyo
Daejonggyo is a modern Korean ethnic religion that venerates the legendary founder Dangun as a divine ancestor and centers on Korean national identity and spiritual heritage.
-
B.
Hanguk Suhwagi
Hanguk Suhwagi is the Korean Sign Language used by the Deaf community in South Korea for everyday communication and cultural expression.
-
C.
Gwanse-eum
Gwanse-eum is the Korean name for Avalokiteśvara, the bodhisattva of compassion revered in Mahayana Buddhism.
-
D.
Geunchogo-wang
Geunchogo-wang was a prominent 4th-century king of the Korean kingdom of Baekje, known for greatly expanding its territory and strengthening its cultural and political influence.
-
E.
Sokdaejeon
Sokdaejeon was an earlier Joseon Dynasty legal code that laid the groundwork for the later, more comprehensive Gyeongguk Daejeon.
- F. None of above. chosen
Provenance (5 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_69e2460389408190be74f41d217799a9 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f19165949c81908e4d66a8a2b0a25a |
completed | April 29, 2026, 5:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c3f4ffc3c8190a971bc5e7d362ae2 |
completed | May 19, 2026, 10:45 a.m. |
| NEDg | Description generation | batch_6a0c405be1188190b6622665e448bbe7 |
completed | May 19, 2026, 10:50 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c40bece448190bb9fd1a3058a1f06 |
completed | May 19, 2026, 10:51 a.m. |
Created at: April 17, 2026, 4:08 p.m.