Triple
T10074658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bass Harbor–Swan’s Island |
E213718
|
entity |
| Predicate | isMainAccessRouteTo |
P50556
|
FINISHED |
| Object | Swan’s Island by vehicle |
—
|
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: Swan’s Island by vehicle | Statement: [Bass Harbor–Swan’s Island, isMainAccessRouteTo, Swan’s Island by vehicle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isMainAccessRouteTo Context triple: [Bass Harbor–Swan’s Island, isMainAccessRouteTo, Swan’s Island by vehicle]
-
A.
isAccessRouteAround
Indicates that one entity serves as an access route that goes around or circumvents another entity.
-
B.
isMajorRouteInSystem
Indicates that a route functions as a primary or significant corridor within a specified transportation or network system.
-
C.
isMajorRouteFor
Indicates that something serves as a primary or heavily used pathway or channel for the movement or flow of something else.
-
D.
isStandardRouteOn
Indicates that a particular route is the default or officially designated path used on a given transportation line or service.
-
E.
isRouteFor
chosen
Indicates that one entity serves as a path, course, or channel used for traveling, transporting, or connecting to another entity.
- 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_69ca839add308190b57d53b4ec21f2d0 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdd017b8288190a577bd66e4ba66b7 |
completed | April 2, 2026, 2:10 a.m. |
| PD | Predicate disambiguation | batch_69cd4b97870481908f7a89df10d58a9e |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 8:59 p.m.