Triple
T8360754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malham Cove |
E196999
|
entity |
| Predicate | hasRockFormationType |
P4015
|
FINISHED |
| Object | escarpment |
—
|
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: escarpment | Statement: [Malham Cove, hasRockFormationType, escarpment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRockFormationType Context triple: [Malham Cove, hasRockFormationType, escarpment]
-
A.
hasRockType
Indicates that an entity is composed of, characterized by, or associated with a specific type of rock.
-
B.
geologicalFormation
chosen
Indicates that one entity is a geological structure or feature that characterizes or composes the physical makeup of another entity.
-
C.
geologicType
Indicates the specific geological classification or category assigned to a rock, soil, or earth material unit.
-
D.
hasTypeOfTectonicFeature
Indicates that one entity is characterized by or classified as a specific type of tectonic feature (such as a fault, plate boundary, or rift).
-
E.
rockTypeMarketedAs
Indicates that a particular rock type is promoted or advertised under a specific commercial or trade name.
- 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_69ca82f2dbe48190aba982e75a0d94de |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb80728eb081909bae6aae45848fab |
completed | March 31, 2026, 8:06 a.m. |
| PD | Predicate disambiguation | batch_69cb70ca25548190b0f90c5384e3fb3c |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6 p.m.