Triple
T25269564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ceredigion (upper catchment vicinity) |
E633529
|
entity |
| Predicate | watercourseBegins |
P25636
|
FINISHED |
| Object | River Tywi |
—
|
NE NERFINISHED |
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: River Tywi | Statement: [Ceredigion (upper catchment vicinity), watercourseBegins, River Tywi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: watercourseBegins Context triple: [Ceredigion (upper catchment vicinity), watercourseBegins, River Tywi]
-
A.
watercourseFor
Indicates that one entity serves as the watercourse (such as a river or channel) associated with, carrying, or draining another entity.
-
B.
sourceOfWatercourse
chosen
Indicates that one entity is the origin or starting point from which a watercourse (such as a river or stream) begins or flows.
-
C.
watercourseProgression
Indicates the downstream sequence in which a watercourse flows into other water bodies or watercourses.
-
D.
riverFormed
Indicates that a river came into existence or was created, typically as a result of natural geological or hydrological processes.
-
E.
watercourseFeature
Indicates that a feature is a physical characteristic or component associated with a watercourse (such as a river, stream, or canal).
- 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_69e75a92f48881909974ff9c11150a2e |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f48ba023b481908b6c6caf212818a3 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f4806d93dc8190b9dff4c63186faff |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 1:16 p.m.