Triple
T432151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sea of Azov |
E9735
|
entity |
| Predicate | hasSedimentSource |
P2051
|
FINISHED |
| Object | Don River sediments |
—
|
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: Don River sediments | Statement: [Sea of Azov, hasSedimentSource, Don River sediments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSedimentSource Context triple: [Sea of Azov, hasSedimentSource, Don River sediments]
-
A.
hasSedimentLoad
Indicates that one entity (typically a water body or flow) carries or transports a certain amount or type of sediment associated with another entity.
-
B.
sedimentSource
chosen
Indicates that one entity serves as the origin or provider of sediment that is transported to or deposited in another entity.
-
C.
typeOfSedimentation
Indicates the specific kind or process of sediment deposition or settling that characterizes how sediment accumulates in a given context.
-
D.
hasSoil
Indicates that one entity possesses, contains, or is associated with a particular type or instance of soil.
-
E.
hasRiverActivity
Indicates that an entity engages in, supports, or is associated with activities occurring on or along a river.
- 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_69a2e801e1d48190b505d1dd336b52ac |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2eef07e748190b05392778f3de980 |
completed | Feb. 28, 2026, 1:34 p.m. |
| PD | Predicate disambiguation | batch_69a2edd9264c8190b92f9a50348e5541 |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.