Triple
T12831435
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philadelphia subway system |
E306795
|
entity |
| Predicate | fareSystem |
P395
|
FINISHED |
| Object | SEPTA Key |
E6321
|
NE 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: SEPTA Key | Statement: [Philadelphia subway system, fareSystem, SEPTA Key]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SEPTA Key Context triple: [Philadelphia subway system, fareSystem, SEPTA Key]
-
A.
SEPTA Key
chosen
SEPTA Key is a contactless smart fare card and payment system used across Philadelphia’s SEPTA public transit network.
-
B.
SmarTrip
SmarTrip is a rechargeable contactless smart card used to pay fares on the Washington, D.C. region’s public transit systems.
-
C.
Metro TAP card
The Metro TAP card is a reusable, reloadable smart fare card used for contactless payment across the Los Angeles County public transit system.
-
D.
TransLink card
The TransLink card was a contactless smart card used for fare payment on public transit systems in the San Francisco Bay Area before being succeeded by the Clipper card.
-
E.
SmartRider card
The SmartRider card is a reusable contactless smartcard used for electronic ticketing on Transperth public transport services in Western Australia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d7bdf52b94819096d6f0ba4ab50a98 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96fb0bb208190bdc4d3dc7909be06 |
completed | April 10, 2026, 9:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f68ed8d20081908e0fb5262b354cab |
completed | May 2, 2026, 11:55 p.m. |
Created at: April 9, 2026, 5:34 p.m.