Triple
T9212347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Saint-Pierre |
E221153
|
entity |
| Predicate | wetlandsType |
P24156
|
FINISHED |
| Object | freshwater marshes |
—
|
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: freshwater marshes | Statement: [Lake Saint-Pierre, wetlandsType, freshwater marshes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wetlandsType Context triple: [Lake Saint-Pierre, wetlandsType, freshwater marshes]
-
A.
formsWetland
Indicates that one entity creates, develops, or gives rise to a wetland environment in relation to another entity or location.
-
B.
containsWetland
chosen
Indicates that one area or region includes within its boundaries a wetland ecosystem.
-
C.
RamsarSite
Indicates that a wetland has been designated as a Ramsar Site, meaning it is recognized under the Ramsar Convention as a wetland of international importance.
-
D.
watershedType
Indicates the classification or category of a watershed associated with an entity (e.g., by hydrologic, ecological, or management type).
-
E.
hasWetlandsAtMouth
Indicates that a watercourse or water body has wetlands located at or surrounding its mouth where it meets another body of water.
- 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_69ca83e9d0e081908bdb71097201a06c |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccd9b69838819088f33ca995fce222 |
completed | April 1, 2026, 8:39 a.m. |
| PD | Predicate disambiguation | batch_69cc660ce23c81909c7bbe10f4a05f36 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:27 p.m.