Triple
T33859594
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flames Across the Border |
E867885
|
entity |
| Predicate | hasCanadianSubject |
P197298
|
FINISHED |
| Object | Upper Canada |
—
|
NE NERFINISHED |
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: Upper Canada | Statement: [Flames Across the Border, hasCanadianSubject, Upper Canada]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCanadianSubject Context triple: [Flames Across the Border, hasCanadianSubject, Upper Canada]
-
A.
hasAmericanSubject
Indicates that the subject of the relationship is an American entity (e.g., person, organization, or work).
-
B.
hasLanguageOnCanadianSide
Indicates that a specified language is used or present on the Canadian side of a border, region, or context.
-
C.
hasHumanSubject
Indicates that an entity serves as the human participant or subject involved in an action, event, or relation.
-
D.
hasSubjectPeople
chosen
Indicates that something (such as a work, document, or record) has people as its primary subject or focus.
-
E.
includesCanadianTerritoryPartially
Indicates that one entity geographically encompasses part, but not all, of the territory of Canada.
- 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_69f349943ccc8190a3c41a3e0ae46cbf |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff41645c548190b7cb4e53079b93ef |
completed | May 9, 2026, 2:15 p.m. |
| PD | Predicate disambiguation | batch_69ff410aa33c8190869ba769ac2a93ce |
completed | May 9, 2026, 2:13 p.m. |
Created at: May 1, 2026, 1:47 a.m.