Triple
T25473650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Korean railway network |
E638370
|
entity |
| Predicate | hasConventionalMainLine |
P3492
|
FINISHED |
| Object | Gyeongbu Line |
—
|
NE NERFINISHED |
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: Gyeongbu Line | Statement: [South Korean railway network, hasConventionalMainLine, Gyeongbu Line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasConventionalMainLine Context triple: [South Korean railway network, hasConventionalMainLine, Gyeongbu Line]
-
A.
hasMainTrunkLine
chosen
Indicates that an entity is connected to or served by a primary or central trunk line within a network or system.
-
B.
hasMainStraight
Indicates that an entity (such as a race track or road) includes a primary, central straight section used as its main straightaway.
-
C.
mainLine
Indicates that something serves as the primary or central line, route, or sequence among a set of related lines.
-
D.
hasMajorBranch
Indicates that one entity possesses or includes another entity as a primary or principal subdivision or branch.
-
E.
hasMainArch
Indicates that an entity possesses or features a primary or central arch structure.
- 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_69e75db9b964819096802dcf502e577e |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f79f48acec8190a9d5964581a94f6c |
completed | May 3, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69f79e4888248190be2f63cdfb5cd7b7 |
completed | May 3, 2026, 7:13 p.m. |
Created at: April 21, 2026, 2:25 p.m.