Triple
T24620665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grant City station |
E609401
|
entity |
| Predicate | hasSouthboundDirection |
P102964
|
FINISHED |
| Object | toward Tottenville |
—
|
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: toward Tottenville | Statement: [Grant City station, hasSouthboundDirection, toward Tottenville]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSouthboundDirection Context triple: [Grant City station, hasSouthboundDirection, toward Tottenville]
-
A.
hasSouthboundServicesTo
chosen
Indicates that a location provides transportation services traveling in a generally southward direction to another location.
-
B.
hasSouthboundPlatform
Indicates that an entity includes or is associated with a platform designated for southbound travel or service.
-
C.
hasNorthboundServicesTo
Indicates that an entity provides or supports services that travel or operate in a northbound direction to another location or entity.
-
D.
hasSouthExit
Indicates that an entity has an exit or passage leading toward the south.
-
E.
hasDirectionType
Indicates that something possesses or is associated with a specific type or category of direction.
- 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_69e2c4d1140081909c58667bf68f80c3 |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6ca751c8190a040c10d701ecf3a |
completed | April 30, 2026, 12:48 a.m. |
Created at: April 18, 2026, 2:32 a.m.