Triple
T21094916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hakodate Main Line |
E519736
|
entity |
| Predicate | connectsToAirportVia |
P23780
|
FINISHED |
| Object | Chitose Line to New Chitose Airport |
—
|
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: Chitose Line to New Chitose Airport | Statement: [Hakodate Main Line, connectsToAirportVia, Chitose Line to New Chitose Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsToAirportVia Context triple: [Hakodate Main Line, connectsToAirportVia, Chitose Line to New Chitose Airport]
-
A.
connectsWithAirport
chosen
Indicates that there is a direct transportation or operational link established between an entity and an airport.
-
B.
servesPassengerTrafficTo
Indicates that a transportation facility or service provides regular passenger traffic access or operations to a particular location or area.
-
C.
servesFlightsTo
Indicates that one transportation provider regularly operates flights to a specified destination location.
-
D.
associatedAirportServes
Indicates that a given airport provides service to, or is used by, the associated entity (such as a city, region, or facility).
-
E.
associatedAirport
Indicates a relationship where an entity is linked or connected to a specific airport, typically as its relevant or corresponding airport.
- 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_69e0b508d8dc81909be940dafe36c8f7 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e71b5845f88190a16f3df157f0906c |
completed | April 21, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_69e5dbfcd5e881908f1e4e0d2d237856 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:52 p.m.