Triple
T21296394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kasabonika Lake First Nation |
E524933
|
entity |
| Predicate | secondaryAccess |
P50364
|
FINISHED |
| Object | winter road |
—
|
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: winter road | Statement: [Kasabonika Lake First Nation, secondaryAccess, winter road]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondaryAccess Context triple: [Kasabonika Lake First Nation, secondaryAccess, winter road]
-
A.
secondaryAccessMode
chosen
Indicates an additional, non-primary way in which an entity can be accessed, used, or interacted with.
-
B.
secondaryAuthority
Indicates that an entity holds a subordinate or supporting level of authority relative to a primary authority within a given context.
-
C.
secondaryTo
Indicates that one condition, event, or factor occurs as a consequence of, or is caused by, another primary condition, event, or factor.
-
D.
secondarySee
Indicates that one entity is referenced as an additional or alternative point of consultation or viewing in relation to another entity.
-
E.
secondaryResource
Indicates that a resource serves as a secondary, supporting, or auxiliary resource in relation to a primary one.
- 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_69e0b517e6748190850d6f6ddf323d69 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7385858ec8190bdc9c5cdcb8d4507 |
completed | April 21, 2026, 8:42 a.m. |
| PD | Predicate disambiguation | batch_69e61612ab748190a72b8703b938abcb |
completed | April 20, 2026, 12:03 p.m. |
Created at: April 16, 2026, 4:04 p.m.