Triple
T346953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Seine |
E6962
|
entity |
| Predicate | tributary |
P415
|
FINISHED |
| Object | Marne |
E46315
|
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: Marne | Statement: [River Seine, tributary, Marne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marne Context triple: [River Seine, tributary, Marne]
-
A.
Marne
chosen
The Marne is a major river in northeastern France that flows through the Île-de-France region before joining the Seine near Paris.
-
B.
Nièvre
Nièvre is a rural department in central France’s Bourgogne-Franche-Comté region, known for its rolling countryside, the Loire River, and its capital city Nevers.
-
C.
Yonne
Yonne is a major river in north-central France that flows through the Burgundy region before joining the Seine.
-
D.
Allier River
The Allier River is a major river in central France, known for its largely unspoiled natural course and as a tributary of the Loire.
-
E.
Source-Seine
Source-Seine is the small commune in eastern France where the River Seine originates.
- 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_69a2e7951ba08190960e90823b5078f3 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eb1a37c08190b1380f6bf8513a37 |
completed | Feb. 28, 2026, 1:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3f0a2d7b08190a99a85a79e69a717 |
completed | March 1, 2026, 7:54 a.m. |
Created at: Feb. 28, 2026, 1:08 p.m.