Triple
T7679155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Compiègne |
E173943
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Oise River |
E326194
|
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: Oise River | Statement: [Compiègne, locatedOn, Oise River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oise River Context triple: [Compiègne, locatedOn, Oise River]
-
A.
Oise River
chosen
The Oise River is a major waterway in northern France and southern Belgium that flows into the Seine and serves as an important route for inland navigation and commerce.
-
B.
Aube River
The Aube River is a major waterway in northeastern France that flows through the Champagne region before joining the Seine.
-
C.
Sée River
The Sée River is a coastal river in northwestern France that flows through Normandy before emptying into the Bay of Mont-Saint-Michel.
-
D.
Assineau River
The Assineau River is a small river in north-central Alberta, Canada, that drains surrounding forested and rural areas before emptying into Lesser Slave Lake.
-
E.
Essonne River
The Essonne River is a tributary of the Seine in northern France, flowing through the Île-de-France region and giving its name to the Essonne department.
- 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_69c6995703e0819081de77361b602e78 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c701fe2cc88190b5fd5e1378c32e5b |
completed | March 27, 2026, 10:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfeaaf9ea0819091bd0981068e5a72 |
completed | April 3, 2026, 4:28 p.m. |
Created at: March 27, 2026, 4:01 p.m.