Triple
T10070318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Auvergne |
E213603
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Volvic |
E147857
|
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: Volvic | Statement: [Auvergne, contains, Volvic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Volvic Context triple: [Auvergne, contains, Volvic]
-
A.
Volvic
chosen
Volvic is a French town in the Auvergne region best known worldwide for its natural mineral water sourced from volcanic springs.
-
B.
Vittel
Vittel is a French spa town renowned for its mineral water springs and bottled water brand, located in northeastern France.
-
C.
Perrier
Perrier is a French brand of naturally carbonated mineral water known for its distinctive green bottles and strong sparkling taste.
-
D.
Valser mineral water
Valser mineral water is a Swiss bottled mineral water brand sourced from the alpine springs of Vals, known for its purity and distinctive mineral composition.
-
E.
Fiji Water
Fiji Water is a premium bottled water brand sourced from an artesian aquifer in Fiji and marketed worldwide for its purity and distinctive square bottles.
- 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_69ca839add308190b57d53b4ec21f2d0 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdcffa045c8190a08db0bb74cb006a |
completed | April 2, 2026, 2:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d29aa05cc881909f59178e9c6c01ef |
completed | April 5, 2026, 5:23 p.m. |
Created at: March 30, 2026, 8:58 p.m.