Triple
T19919881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mt. Lebanon station |
E478761
|
entity |
| Predicate | fareSystem |
P395
|
FINISHED |
| Object | ConnectCard |
—
|
NE NERFINISHED |
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: ConnectCard | Statement: [Mt. Lebanon station, fareSystem, ConnectCard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ConnectCard Context triple: [Mt. Lebanon station, fareSystem, ConnectCard]
-
A.
ConnectCard
chosen
ConnectCard is a reusable smart fare card used by Pittsburgh Regional Transit riders to pay for public transportation across the Pittsburgh area.
-
B.
Connect Card
Connect Card is a regional smart transit fare card system used for contactless payment across public transportation services in the Sacramento area.
-
C.
CharlieCard
The CharlieCard is a reusable contactless smart card used to pay fares on Boston's MBTA public transit system.
-
D.
Metcard
Metcard was Melbourne’s former magnetic stripe ticketing system used for public transport before the introduction of the Myki smartcard.
-
E.
Credo Card
Credo Card is a core service philosophy tool used by The Ritz-Carlton Hotel Company to communicate and reinforce its brand standards, values, and commitment to exceptional guest service among employees.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659c49d408190b3a42bada3675133 |
completed | April 20, 2026, 4:52 p.m. |
Created at: April 10, 2026, 1:53 p.m.