Triple
T3455191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tonnerre |
E72887
|
entity |
| Predicate | river |
P165
|
FINISHED |
| Object | Armançon |
E287728
|
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: Armançon | Statement: [Tonnerre, river, Armançon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Armançon Context triple: [Tonnerre, river, Armançon]
-
A.
Armançon
chosen
Armançon is a river in central-eastern France that flows through the Burgundy region before joining the Yonne River.
-
B.
Clessé
Clessé is a wine-producing village in the Mâconnais region of Burgundy, France, known for its quality white wines.
-
C.
Cugny
Cugny is a locality within the municipality of Bernex in the canton of Geneva, Switzerland.
-
D.
Pougny
Pougny is a small French commune, likely located near the Swiss border in the Auvergne-Rhône-Alpes region.
-
E.
La Dôle
La Dôle is a prominent mountain peak in the Jura range of western Switzerland, known for its panoramic views over Lake Geneva and the Alps and for hosting telecommunications and weather facilities near its summit.
- 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_69ad85b12a908190a1d10a6b03b4f8ae |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbaa5e2188190a8157cb8dcca8d30 |
completed | March 8, 2026, 6:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b53fd1a2088190b43cded6c0e90633 |
completed | March 14, 2026, 11 a.m. |
Created at: March 8, 2026, 3:16 p.m.