Triple
T9416604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MBTA State Street station |
E227035
|
entity |
| Predicate | hasBicyclePolicy |
P89031
|
FINISHED |
| Object | bicycles not allowed on platforms during peak hours |
—
|
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: bicycles not allowed on platforms during peak hours | Statement: [MBTA State Street station, hasBicyclePolicy, bicycles not allowed on platforms during peak hours]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBicyclePolicy Context triple: [MBTA State Street station, hasBicyclePolicy, bicycles not allowed on platforms during peak hours]
-
A.
hasBicycleFacilities
Indicates that appropriate bicycle-related infrastructure or amenities are available at or associated with the subject.
-
B.
bicyclesAllowed
Indicates that bicycles are permitted to use or access a particular route, area, or facility.
-
C.
hasRideCycle
Indicates that one entity is associated with, or participates in, a recurring sequence or cycle of rides or ride operations.
-
D.
bicycleUse
Indicates that an entity makes use of a bicycle for transportation, activity, or other purposes.
-
E.
bicycleType
Indicates the specific kind or category of bicycle associated with an entity.
- F. None of above. chosen
Provenance (4 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_69ca84359e7c819091148ba4b670e436 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd68c9917481909f793a2a9efb2a75 |
completed | April 1, 2026, 6:49 p.m. |
| PD | Predicate disambiguation | batch_69cca54c37f88190bddccf28e5fe5c84 |
completed | April 1, 2026, 4:55 a.m. |
| PDg | Predicate description generation | batch_69cca9d07eb08190866eb15333386dfa |
completed | April 1, 2026, 5:14 a.m. |
Created at: March 30, 2026, 7:48 p.m.