Triple
T32045936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Campostoma |
E818349
|
entity |
| Predicate | foundInDrainage |
P195939
|
FINISHED |
| Object | Mississippi River basin |
—
|
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: Mississippi River basin | Statement: [Campostoma, foundInDrainage, Mississippi River basin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foundInDrainage Context triple: [Campostoma, foundInDrainage, Mississippi River basin]
-
A.
hasDrainage
Indicates that one entity serves as the drainage system or outlet through which another entity’s liquid or runoff is removed or discharged.
-
B.
drainageOutlet
Indicates that one entity serves as the point where fluids or runoff are discharged or exit from another entity.
-
C.
drainageBetween
Indicates that one area or feature serves as a drainage path or channel between two other areas or features, allowing water or runoff to flow from one to the other.
-
D.
drainageType
Indicates the kind or classification of drainage associated with or applied to an entity (e.g., how water is removed or flows from it).
-
E.
drainsNear
Indicates that one entity, typically a drainage feature or outlet, is located in close proximity to another relevant object or area.
- F. None of above. chosen
Provenance (4 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_69f348fcfb648190859f6be5e04b7cfe |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fdf5d05cc481909ec9e1b1f0784279 |
completed | May 8, 2026, 2:40 p.m. |
| PD | Predicate disambiguation | batch_69fdf0cdd6948190838864ab3120dfa6 |
completed | May 8, 2026, 2:18 p.m. |
| PDg | Predicate description generation | batch_69fdf5cfa1ec8190b80d887fa1bfb4cf |
completed | May 8, 2026, 2:40 p.m. |
Created at: May 1, 2026, 12:20 a.m.