Triple
T18700525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orne bridges |
E457236
|
entity |
| Predicate | crosses |
P416
|
FINISHED |
| Object | Orne River |
—
|
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: Orne River | Statement: [Orne bridges, crosses, Orne River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Orne River Context triple: [Orne bridges, crosses, Orne River]
-
A.
Orne River
chosen
The Orne River is a waterway in northwestern France that flows through Normandy before emptying into the English Channel at the port town of Ouistreham.
-
B.
Peabody River
The Peabody River is a mountain river in New Hampshire’s White Mountains that drains the Pinkham Notch area before joining the Androscoggin River.
-
C.
Mad River
Mad River is a smaller river in British Columbia, Canada, that feeds into the North Thompson River within the Fraser River watershed.
-
D.
Mad River
Mad River is a tributary of the Great Miami River in western Ohio known for its clear, cold waters and popularity for fishing and paddling.
-
E.
Mad River
Mad River is a tributary stream in New Hampshire that feeds into the Pemigewasset River within the Merrimack River watershed.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8d392aad081909fe31aa03e6e97d1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e562eb06b481908ef9efdb976008f3 |
completed | April 19, 2026, 11:19 p.m. |
Created at: April 10, 2026, 11:49 a.m.