Triple
T8980921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 금정구 |
E214521
|
entity |
| Predicate | hasReligiousSite |
P916
|
FINISHED |
| Object | 범어사 |
E769258
|
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: 범어사 | Statement: [금정구, hasReligiousSite, 범어사]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 범어사 Context triple: [금정구, hasReligiousSite, 범어사]
-
A.
범어사
chosen
범어사는 부산 금정산 자락에 위치한 통도사·해인사와 함께 영남 3대 사찰로 꼽히는 유서 깊은 대한불교조계종 사찰이다.
-
B.
범어사역
범어사역은 부산 도시철도 1호선의 북쪽 끝자락에 위치해 범어사와 금정산 일대 관광지로 가는 관문 역할을 하는 지하철역이다.
-
C.
Imjin Waeran
Imjin Waeran refers to the late 16th-century Japanese military campaigns led by Toyotomi Hideyoshi to conquer Korea as a route to invade China, which resulted in massive devastation on the Korean Peninsula and significant regional power shifts in East Asia.
-
D.
Dal-dong
Dal-dong is a neighborhood in Ulsan, South Korea, known for encompassing the large urban green space of Ulsan Grand Park.
-
E.
Osancheon
Osancheon is a river in Osan, South Korea, that flows through the city and serves as a local natural and recreational landmark.
- 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_69ca839ea8b88190922c6a326ffcc0d3 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc67a76f748190a4abad5d53d58fa8 |
completed | April 1, 2026, 12:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfdb8de5e081909cce650a0b299e85 |
completed | April 3, 2026, 3:23 p.m. |
Created at: March 30, 2026, 7:03 p.m.