Triple
T30184418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Ounianga UNESCO World Heritage Site |
E767295
|
entity |
| Predicate | geologicalPeriodOfAquifer |
P1327
|
FINISHED |
| Object | Quaternary |
—
|
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: Quaternary | Statement: [Lake Ounianga UNESCO World Heritage Site, geologicalPeriodOfAquifer, Quaternary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: geologicalPeriodOfAquifer Context triple: [Lake Ounianga UNESCO World Heritage Site, geologicalPeriodOfAquifer, Quaternary]
-
A.
aquiferType
Indicates the classification or category of an aquifer based on its hydrogeologic characteristics or behavior.
-
B.
aquiferMaterial
Indicates that one entity serves as the material or geologic substance composing or characterizing an aquifer associated with another entity.
-
C.
formsAquifers
Indicates that something creates, develops, or contributes to the formation of aquifers as groundwater-bearing geological structures.
-
D.
geologicalAge
chosen
Indicates the time period in Earth's geological history during which an entity (such as a rock, fossil, or formation) originated or was formed.
-
E.
hasAquifer
Indicates that one entity possesses, contains, or overlies an aquifer associated with it.
- 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_69f2247cc3d88190811dec3face94bf5 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68f670b608190a0b6ab60d722b4e0 |
completed | May 2, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69f68b7b03488190b1db5fde4c7dd6e5 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 29, 2026, 7:27 p.m.