Triple
T16052467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swartland |
E389388
|
entity |
| Predicate | mainGrapeVariety |
P975
|
FINISHED |
| Object | Roussanne |
E291116
|
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: Roussanne | Statement: [Swartland, mainGrapeVariety, Roussanne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roussanne Context triple: [Swartland, mainGrapeVariety, Roussanne]
-
A.
Roussanne
chosen
Roussanne is a white wine grape variety from France known for producing aromatic, full-bodied wines with notes of pear, herbal tea, and honey, and is especially associated with the Rhône Valley.
-
B.
Viognier
Viognier is a white wine grape variety known for producing aromatic, full-bodied wines with notes of stone fruit, floral aromas, and rich texture.
-
C.
Marsanne
Marsanne is a white wine grape variety from France’s Rhône Valley, known for producing full-bodied, aromatic wines often blended with Roussanne.
-
D.
Marsanne
Marsanne is a commune in the Drôme department of southeastern France, known for its historic village setting amid the Rhône Valley countryside.
-
E.
Chenin Blanc
Chenin Blanc is a versatile white wine grape variety from France’s Loire Valley, known for producing wines ranging from dry and sparkling to richly sweet, with high acidity and notes of apple, honey, and floral aromas.
- 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_69d86dae698881908327ef2d67706cb9 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e183627bd88190bf94054de13a7733 |
completed | April 17, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffeb8b1b2c8190949943b20f2f8574 |
completed | May 10, 2026, 2:20 a.m. |
Created at: April 10, 2026, 4:56 a.m.