Triple
T18950589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fifth Avenue–53rd Street |
E463635
|
entity |
| Predicate | crossPlatformTransfers |
P32010
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Fifth Avenue–53rd Street, crossPlatformTransfers, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crossPlatformTransfers Context triple: [Fifth Avenue–53rd Street, crossPlatformTransfers, yes]
-
A.
crossPlatformWith
Indicates that two systems, applications, or components are compatible with or operate across multiple platforms together.
-
B.
transferBetween
Indicates a movement or handover of something from one entity to another, typically changing its location, ownership, or control between them.
-
C.
transferType
Indicates the specific method or category of how something is transferred from one entity to another.
-
D.
hasCrossPlatformInterchange
chosen
Indicates that there is a transfer point where passengers can switch between different transportation platforms or modes within the same location.
-
E.
transferMode
Indicates the method or mechanism by which something is transferred from one entity to another.
- 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_69d8dcfec90481909e926be9767e5779 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d542b238819089ccd2df279a2f7f |
completed | April 20, 2026, 7:26 a.m. |
| PD | Predicate disambiguation | batch_69e4a2efec5c8190840704016bf547a1 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, noon