Triple
T15102203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rohrbach (Breg tributary) |
E360695
|
entity |
| Predicate | tributaryOf |
P415
|
FINISHED |
| Object | Breg |
E69261
|
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: Breg | Statement: [Rohrbach (Breg tributary), tributaryOf, Breg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Breg Context triple: [Rohrbach (Breg tributary), tributaryOf, Breg]
-
A.
Breg
chosen
Breg is a river in Germany’s Black Forest region that forms one of the main headwaters of the Danube.
-
B.
Breage
Breage is a rural village and civil parish in west Cornwall, England, known for its historic church and traditional Cornish mining heritage.
-
C.
Brey
Brey is the paternal surname of Spanish politician Mariano Rajoy Brey, who served as Prime Minister of Spain from 2011 to 2018.
-
D.
Breng
Breng is a Dutch public transport operator providing regional bus and train services in and around Arnhem and Nijmegen in the Netherlands.
-
E.
Bongrand
Bongrand is a fictional character in Émile Zola’s novel *L’Œuvre*, depicted as an older, established painter who contrasts with the avant-garde ambitions of the protagonist.
- 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_69d85a0491ec8190830960be8fafb994 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00550007481909e02ee1d597a4d37 |
completed | April 15, 2026, 9:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feae2571f48190b73f0aecd113fed6 |
completed | May 9, 2026, 3:46 a.m. |
Created at: April 10, 2026, 3:05 a.m.