Triple
T11394522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horse Cave karst area |
E269937
|
entity |
| Predicate | hasGeologyType |
P89872
|
FINISHED |
| Object | karst |
—
|
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: karst | Statement: [Horse Cave karst area, hasGeologyType, karst]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGeologyType Context triple: [Horse Cave karst area, hasGeologyType, karst]
-
A.
hasGeologicalNature
chosen
Indicates that something possesses a specific geological character, composition, or formation type.
-
B.
geologicType
Indicates the specific geological classification or category assigned to a rock, soil, or earth material unit.
-
C.
hasGeologicalUnit
Indicates that an entity is associated with or contains a specific geological unit, such as a rock layer, formation, or stratigraphic unit.
-
D.
hasGeologicResource
Indicates that an entity possesses, contains, or is associated with a particular geologic resource.
-
E.
hasRockType
Indicates that an entity is composed of, characterized by, or associated with a specific type of rock.
- 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_69d6aacdbc6c8190af6dc3d5f5d22836 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d80018a58c81908b80dc9abd18d650 |
completed | April 9, 2026, 7:38 p.m. |
| PD | Predicate disambiguation | batch_69d7e70b228c8190b87f5101fd683788 |
completed | April 9, 2026, 5:51 p.m. |
Created at: April 8, 2026, 9:34 p.m.