Triple
T28286771
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haneda Airport Terminal 2 Station |
E713303
|
entity |
| Predicate | railAccessFor |
P56141
|
FINISHED |
| Object | domestic flights at Haneda 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: domestic flights at Haneda Airport | Statement: [Haneda Airport Terminal 2 Station, railAccessFor, domestic flights at Haneda Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railAccessFor Context triple: [Haneda Airport Terminal 2 Station, railAccessFor, domestic flights at Haneda Airport]
-
A.
railAccessModel
Indicates the type or pattern of how rail infrastructure or services are accessed or connected between locations or entities.
-
B.
railwayAccess
Indicates that an entity has direct access to, connection with, or service by a railway line or station.
-
C.
hasRailOrRoadAccess
Indicates that an entity is connected to or reachable by either a railway network, a road network, or both.
-
D.
endStationProvidesAccessTo
Indicates that a particular end station offers access or connectivity to another location, service, or network resource.
-
E.
accessibleFromStation
chosen
Indicates that a location or facility can be reached directly or conveniently starting from a given station.
- 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_69efb52371d88190a1381c4e58a3b731 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f6448075c48190a28340ceb79c7d3e |
completed | May 2, 2026, 6:37 p.m. |
| PD | Predicate disambiguation | batch_69f641e0fde08190bf06a1c5b388aa84 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 27, 2026, 11:26 p.m.