Triple
T9077627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arlington Cemetery station |
E217527
|
entity |
| Predicate | fareCollectionLocation |
P8430
|
FINISHED |
| Object | surface mezzanine |
—
|
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: surface mezzanine | Statement: [Arlington Cemetery station, fareCollectionLocation, surface mezzanine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fareCollectionLocation Context triple: [Arlington Cemetery station, fareCollectionLocation, surface mezzanine]
-
A.
fareCollectionType
Indicates the method or system used to collect fares or payments for a service.
-
B.
fareControlLocation
chosen
Indicates a location where access to or use of a transportation service is regulated, checked, or controlled for fare payment.
-
C.
ticketingLocation
Indicates the place or point where tickets are issued, sold, or otherwise processed for an event, service, or journey.
-
D.
fareControlUnifiedWith
Indicates that separate fare control areas are combined into a single, shared fare-controlled zone.
-
E.
fareIntegration
Indicates that multiple transportation services or modes share a coordinated fare system, allowing passengers to use a single payment or ticket across them.
- 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_69ca83d6c14c8190bc056d927f00a2a2 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc95c7d3688190a4c1c6a92965eae4 |
completed | April 1, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69cc65fa79bc81908b46f05c8bba920f |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:12 p.m.