Triple
T19752958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Ebbw |
E474427
|
entity |
| Predicate | flowsThrough |
P225
|
FINISHED |
| Object | Risca |
E117223
|
NE 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: Risca | Statement: [River Ebbw, flowsThrough, Risca]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Risca Context triple: [River Ebbw, flowsThrough, Risca]
-
A.
Risca
chosen
Risca is a town in south Wales situated in the county borough of Caerphilly, near Newport, with a history rooted in coal mining and industry.
-
B.
Brunete
Brunete is a town in the Community of Madrid, Spain, historically notable as a major battleground of the Spanish Civil War.
-
C.
Baarìa
Baarìa is an Italian epic drama film directed by Giuseppe Tornatore that chronicles several generations of life, politics, and love in a Sicilian town.
-
D.
Colomars
Colomars is a small commune in southeastern France situated in the hills northwest of Nice, known for its scenic Mediterranean landscape and proximity to the French Riviera.
-
E.
Clara-Villerach
Clara-Villerach is a small commune in the Pyrénées-Orientales department of southern France, known for its rural setting in the historic Conflent region.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8e51940a0819087bd2996f98da668 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6529bcb8c8190bcca61a53be86757 |
completed | April 20, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07bd64ff708190bf23345b53ad6d0d |
completed | May 16, 2026, 12:42 a.m. |
Created at: April 10, 2026, 1:48 p.m.