Triple
T24775277
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaohsiung MRT Red Line |
E619843
|
entity |
| Predicate | stationServing |
P96283
|
FINISHED |
| Object | Kaohsiung International Airport Station |
—
|
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: Kaohsiung International Airport Station | Statement: [Kaohsiung MRT Red Line, stationServing, Kaohsiung International Airport Station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stationServing Context triple: [Kaohsiung MRT Red Line, stationServing, Kaohsiung International Airport Station]
-
A.
stationName
Indicates the name assigned to a particular station in the relationship.
-
B.
stationNumber
Indicates the specific station identifier or code assigned to an entity within a system or network.
-
C.
stationOnLine
chosen
Indicates that a particular station is located on or served by a specific transit line.
-
D.
stationType
Indicates the specific category or classification of a station based on its function, services, or operational characteristics.
-
E.
servesAsThroughStationFor
Indicates that a station functions as an intermediate (through) stop for a particular service, route, or journey rather than as its starting or ending point.
- 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_69e2fabd04488190a2d13c97be745a2d |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f42d9000b8819081ea2605f3c193d6 |
completed | May 1, 2026, 4:35 a.m. |
| PD | Predicate disambiguation | batch_69f420f471a0819095a6cd24ed8f7476 |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 4:34 a.m.