Triple
T20914445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Derbyshire–Cheshire border hills |
E515033
|
entity |
| Predicate | hasSurfaceGeology |
P89872
|
FINISHED |
| Object | gritstone |
—
|
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: gritstone | Statement: [Derbyshire–Cheshire border hills, hasSurfaceGeology, gritstone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSurfaceGeology Context triple: [Derbyshire–Cheshire border hills, hasSurfaceGeology, gritstone]
-
A.
surfaceGeologyKnown
Indicates that the composition or characteristics of an entity’s surface geology have been determined or are known.
-
B.
hasRegolith
Indicates that one entity possesses, contains, or is covered by regolith (a layer of loose, unconsolidated surface material).
-
C.
hasHeavilyCrateredSurface
Indicates that the subject’s surface is densely covered with impact craters, showing extensive cratering relative to typical surfaces.
-
D.
hasComplexGeology
Indicates that an entity possesses geologic features or structure that are intricate, varied, or highly heterogeneous rather than simple or uniform.
-
E.
hasGeologicalNature
chosen
Indicates that something possesses a specific geological character, composition, or formation type.
- 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_69e0b4f9d5ec8190bb2bd27350ed341c |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6ec61a6ec81908d9e0629438d27c9 |
completed | April 21, 2026, 3:17 a.m. |
| PD | Predicate disambiguation | batch_69e5c9ac91108190a6700fcdf2f11890 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:48 p.m.