Triple
T16290659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terret Noir |
E395511
|
entity |
| Predicate | relatedVariety |
P37
|
FINISHED |
| Object |
Terret Blanc
Terret Blanc is a traditional French white grape variety from the Languedoc region, historically used in blends for still and sparkling wines.
|
E1204907
|
NE FINISHED |
How this triple was built (4 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: Terret Blanc | Statement: [Terret Noir, relatedVariety, Terret Blanc]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terret Blanc Context triple: [Terret Noir, relatedVariety, Terret Blanc]
-
A.
Piétrain
Piétrain is a village in Walloon Brabant, Belgium, best known as the namesake origin of the Piétrain pig breed.
-
B.
Piquepoul Noir
Piquepoul Noir is a rare, traditional red wine grape variety from southern France, known for producing light, fresh, and aromatic wines often used in blends.
-
C.
Mouton
Mouton is an academic publishing house known for its influential works in linguistics and related fields.
-
D.
Terrier-Rouge
Terrier-Rouge is a commune in northeastern Haiti known for its rural character and agricultural activities within the Nord-Est department.
-
E.
Mouton-Duvernet
Mouton-Duvernet is a Paris Métro station in the 14th arrondissement, serving the Montparnasse area and named after the French general Régis Barthélemy Mouton-Duvernet.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Terret Blanc Triple: [Terret Noir, relatedVariety, Terret Blanc]
Generated description
Terret Blanc is a traditional French white grape variety from the Languedoc region, historically used in blends for still and sparkling wines.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Terret Blanc Target entity description: Terret Blanc is a traditional French white grape variety from the Languedoc region, historically used in blends for still and sparkling wines.
-
A.
Piétrain
Piétrain is a village in Walloon Brabant, Belgium, best known as the namesake origin of the Piétrain pig breed.
-
B.
Piquepoul Noir
Piquepoul Noir is a rare, traditional red wine grape variety from southern France, known for producing light, fresh, and aromatic wines often used in blends.
-
C.
Mouton
Mouton is an academic publishing house known for its influential works in linguistics and related fields.
-
D.
Terrier-Rouge
Terrier-Rouge is a commune in northeastern Haiti known for its rural character and agricultural activities within the Nord-Est department.
-
E.
Mouton-Duvernet
Mouton-Duvernet is a Paris Métro station in the 14th arrondissement, serving the Montparnasse area and named after the French general Régis Barthélemy Mouton-Duvernet.
- F. None of above. chosen
Provenance (5 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_69d87f22c7248190a54c949738441e2e |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2491821d0819086cffdd7551ba85a |
completed | April 17, 2026, 2:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a001f97895081909f22ded3507afe14 |
completed | May 10, 2026, 6:03 a.m. |
| NEDg | Description generation | batch_6a0020c8f904819090bea8655972fa85 |
completed | May 10, 2026, 6:08 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00213560588190850ab5a66fc43704 |
completed | May 10, 2026, 6:09 a.m. |
Created at: April 10, 2026, 5:05 a.m.