Triple
T89985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MBTA bus network |
E1808
|
entity |
| Predicate | fareSystem |
P395
|
FINISHED |
| Object | CharlieCard |
E3327
|
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: CharlieCard | Statement: [MBTA bus network, fareSystem, CharlieCard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CharlieCard Context triple: [MBTA bus network, fareSystem, CharlieCard]
-
A.
CharlieCard
chosen
The CharlieCard is a reusable contactless smart card used to pay fares on Boston's MBTA public transit system.
-
B.
Presto card
The Presto card is a reloadable smart card used for paying public transit fares across the Greater Toronto and Hamilton Area and other regions in Ontario, Canada.
-
C.
CharlieTicket
CharlieTicket is a reusable paper smart card used for paying fares on Boston’s MBTA public transit system.
-
D.
TAP card
The TAP card is a reusable contactless smart card used to pay fares across public transit systems in the Los Angeles County region.
-
E.
Rapid Rewards
Rapid Rewards is Southwest Airlines’ frequent flyer loyalty program that lets members earn points on flights and redeem them for travel and other rewards.
- 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_69a24d1a97dc819094e6c021fe9b05a7 |
completed | Feb. 28, 2026, 2:04 a.m. |
| NER | Named-entity recognition | batch_69a383e3575c8190932dcdc25503d06e |
completed | March 1, 2026, 12:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a38611d3808190834c96fe39f9cf0d |
completed | March 1, 2026, 12:19 a.m. |
Created at: Feb. 28, 2026, 2:07 a.m.