Triple
T8360756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malham Cove |
E196999
|
entity |
| Predicate | hasDrainageType |
P3833
|
FINISHED |
| Object | underground drainage |
—
|
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: underground drainage | Statement: [Malham Cove, hasDrainageType, underground drainage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDrainageType Context triple: [Malham Cove, hasDrainageType, underground drainage]
-
A.
drainageType
chosen
Indicates the kind or classification of drainage associated with or applied to an entity (e.g., how water is removed or flows from it).
-
B.
drainageSystemIncludes
Indicates that a particular drainage system contains or encompasses a specified component, segment, or sub-system as part of its overall structure.
-
C.
drainageStatus
Indicates the condition or effectiveness of water removal or runoff from an area, surface, or system.
-
D.
drainageOutlet
Indicates that one entity serves as the point where fluids or runoff are discharged or exit from another entity.
-
E.
drainagePattern
Indicates the characteristic spatial arrangement and connectivity of natural or artificial drainage features (such as streams, channels, or pipes) within an area.
- 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.