Triple
T28058651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 범어사역 |
E709040
|
entity |
| Predicate | 소속노선 |
P103597
|
FINISHED |
| Object | 부산 도시철도 1호선 |
—
|
LITERAL 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: 부산 도시철도 1호선 | Statement: [범어사역, 소속노선, 부산 도시철도 1호선]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 소속노선 Context triple: [범어사역, 소속노선, 부산 도시철도 1호선]
-
A.
ownsRailwayLine
Indicates that one entity has legal ownership or control over a railway line used for train operations.
-
B.
associatedWithTransitLine
chosen
Indicates that an entity has a connection or linkage to a specific transit line, such as being part of, served by, or otherwise related to that line.
-
C.
situatedOnTransportRoute
Indicates that one entity is located along, on, or directly adjacent to a specified transport route (such as a road, railway, or shipping lane).
-
D.
servedByTramwayLine
Indicates that a location or area is provided public transport service by a specific tramway line.
-
E.
isPublicTransportBackboneOf
Indicates that one transport system serves as the primary structural and functional core of a region’s overall public transportation network.
- F. None of above.
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_69ef9b6eb6d88190a3fea236eb0f7bed |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f63fde4030819089d26a7e7c9d713e |
completed | May 2, 2026, 6:18 p.m. |
| PD | Predicate disambiguation | batch_69f637120c008190b2b5adf46f022e48 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 8:38 p.m.