Triple
T10587387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake of Gruyère |
E249888
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Gruyères |
E808304
|
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: Gruyères | Statement: [Lake of Gruyère, locatedNear, Gruyères]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gruyères Context triple: [Lake of Gruyère, locatedNear, Gruyères]
-
A.
Gruyères
chosen
Gruyères is a picturesque medieval town in the Swiss canton of Fribourg, renowned for its historic architecture, hilltop setting, and namesake cheese.
-
B.
Emmental
Emmental is a rural region in the canton of Bern, Switzerland, known for its rolling hills, dairy farming, and as the origin of Emmental cheese.
-
C.
Vacherin Fribourgeois cheese
Vacherin Fribourgeois cheese is a semi-soft Swiss cow’s milk cheese from the canton of Fribourg, prized for its smooth, melting texture and use in traditional fondues.
-
D.
Brouilly
Brouilly is a French wine appellation in the Beaujolais region, known for its fruity, approachable red wines made primarily from the Gamay grape.
-
E.
Mont d'Or cheese
Mont d'Or cheese is a soft, rich, washed-rind cow’s milk cheese from the Jura region of France, traditionally sold in a spruce-wood box and eaten warm and spoonable.
- 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_69d381c9d3d48190a29ee491e1696a0e |
completed | April 6, 2026, 9:50 a.m. |
| NER | Named-entity recognition | batch_69d5276b0ae48190b2935230363239e0 |
completed | April 7, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d94b8b1b708190865e428128f98720 |
completed | April 10, 2026, 7:12 p.m. |
Created at: April 6, 2026, 12:39 p.m.