Triple
T2122474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Langres Plateau |
E43955
|
entity |
| Predicate | drainedBy |
P165
|
FINISHED |
| Object | upper Seine |
E6962
|
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: upper Seine | Statement: [Langres Plateau, drainedBy, upper Seine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: upper Seine Context triple: [Langres Plateau, drainedBy, upper Seine]
-
A.
Source-Seine
Source-Seine is the small commune in eastern France where the River Seine originates.
-
B.
River Seine
chosen
The River Seine is a major waterway in northern France that flows through the heart of Paris and is central to the city's history, culture, and landscape.
-
C.
Rive Droite
Rive Droite is the northern, historically affluent bank of the Seine in Paris, known for its grand boulevards, major museums, and iconic landmarks.
-
D.
Baie de Seine
Baie de Seine is a coastal bay in northern France where the Seine River meets the English Channel, known for its maritime traffic and proximity to ports like Le Havre.
-
E.
Loing
The Loing is a river in central France that flows through the regions of Burgundy and Île-de-France before joining the Yonne.
- 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_69a88717cfe48190b7ecdd68c824848a |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abbb51e8088190a1aeafee4e8dff63 |
completed | March 7, 2026, 5:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b333ef7f30819086b538cdc2cefe0f |
completed | March 12, 2026, 9:45 p.m. |
Created at: March 4, 2026, 7:44 p.m.