Triple
T6084553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loch of Kirbister |
E135603
|
entity |
| Predicate | hasWaterUse |
P68556
|
FINISHED |
| Object | sport fishing |
—
|
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: sport fishing | Statement: [Loch of Kirbister, hasWaterUse, sport fishing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWaterUse Context triple: [Loch of Kirbister, hasWaterUse, sport fishing]
-
A.
waterUse
Indicates the amount or manner in which water is consumed, utilized, or withdrawn by an entity or activity.
-
B.
hasWatershedUse
Indicates that a particular type of use, activity, or function is associated with or applied to a watershed.
-
C.
hasThermalWaterUse
Indicates that something makes use of thermal water, typically for purposes such as heating, bathing, energy production, or therapeutic applications.
-
D.
usedIrrigation
Indicates that an entity applied or employed an irrigation system or method to supply water to land or crops.
-
E.
waterQualityUse
Indicates the way in which water quality is evaluated, classified, or applied for specific purposes or uses.
- 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_69c0087bcc788190b20f093d3a6c60ec |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c057877b448190aa12d2484102eeaa |
completed | March 22, 2026, 8:56 p.m. |
| PD | Predicate disambiguation | batch_69c049f3b1ec8190bea67a7bec6442a5 |
completed | March 22, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69c04e8d4a148190bd8f95caae978e1b |
completed | March 22, 2026, 8:18 p.m. |
Created at: March 22, 2026, 4:12 p.m.