Triple
T30513126
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gyeongbu Line (local services) |
E776483
|
entity |
| Predicate | primaryRouteEnd |
P203909
|
FINISHED |
| Object | Busan Station |
E36550
|
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: Busan Station | Statement: [Gyeongbu Line (local services), primaryRouteEnd, Busan Station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryRouteEnd Context triple: [Gyeongbu Line (local services), primaryRouteEnd, Busan Station]
-
A.
primaryRoute
Indicates that one route is designated as the main or preferred path among possible alternatives between locations.
-
B.
primaryRouteStart
Indicates the location or point where a primary route or main path begins.
-
C.
primaryRouteOf
Indicates that one route is the main or most important pathway used for reaching or connecting to a particular destination or entity.
-
D.
primaryRouteFrom
Indicates that one entity serves as the main or preferred route originating from another entity.
-
E.
primaryRouteThrough
Indicates that one location or path serves as the main or most significant route passing through another location or area.
- 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_69f2249a155c8190b1d512106007e9bb |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a02efcb13248190a0bef09ba7869ada |
completed | May 12, 2026, 9:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41cc874ae88190bd163e4bcfe569f7 |
completed | June 29, 2026, 1:38 a.m. |
| PD | Predicate disambiguation | batch_6a024995e1d081908783ca294d1397c3 |
completed | May 11, 2026, 9:26 p.m. |
| PDg | Predicate description generation | batch_6a02efca70c48190b724c2a76a09cbfb |
completed | May 12, 2026, 9:15 a.m. |
Created at: April 29, 2026, 8:16 p.m.