Triple
T4632580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Medicine Hat |
E101450
|
entity |
| Predicate | locatedInEcozone |
P948
|
FINISHED |
| Object | Prairies |
—
|
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: Prairies | Statement: [Medicine Hat, locatedInEcozone, Prairies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInEcozone Context triple: [Medicine Hat, locatedInEcozone, Prairies]
-
A.
isEcologicalZone
Indicates that one entity functions as, or is classified as, an ecological zone in relation to another entity.
-
B.
ecozone
Indicates that two entities stand in a biogeographical relationship where one is an ecological zone (ecozone) that characterizes or contains the other.
-
C.
ecoregion
chosen
Indicates that one entity is located within, associated with, or belongs to the same ecological region as another entity.
-
D.
ecoregionsInclude
Indicates that one ecoregion spatially contains or encompasses another ecoregion or area within its boundaries.
-
E.
biogeographicallyRelatedTo
Indicates that two entities are connected through their biogeographic characteristics, such as shared distribution patterns, regions, or historical biogeographic processes.
- 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_69bd43d2f1c081908cd4b7ec48ecc73d |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5a342ffc8190a911d0598ed230bb |
completed | March 20, 2026, 2:31 p.m. |
| PD | Predicate disambiguation | batch_69bd5233cb5081908807e2b150f0ca06 |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:13 p.m.