Triple
T721042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Occitan |
E14615
|
entity |
| Predicate | hasDialect |
P4251
|
FINISHED |
| Object |
Gascon
Gascon is a Romance dialect of the Occitan language traditionally spoken in southwestern France, particularly in the historical region of Gascony.
|
E14615
|
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: Gascon | Statement: [Occitan, hasDialect, Gascon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gascon Context triple: [Occitan, hasDialect, Gascon]
-
A.
Breton
Breton is a Celtic language spoken primarily in Brittany, France, known for its close relation to Cornish and Welsh.
-
B.
Niçard Occitan
Niçard Occitan is a Romance variety of the Occitan language traditionally spoken in and around the city of Nice in southeastern France.
-
C.
Occitan
Occitan is a Romance language historically spoken in southern France and neighboring regions, known for its rich medieval literary tradition and close relation to Catalan.
-
D.
Haketia
Haketia is a Judeo-Spanish dialect historically spoken by Sephardic Jews in northern Morocco and parts of Gibraltar, characterized by strong influences from Moroccan Arabic and Hebrew.
-
E.
Jèrriais
Jèrriais is a Norman Romance language traditionally spoken on the island of Jersey in the Channel Islands.
- 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: Gascon Triple: [Occitan, hasDialect, Gascon]
Generated description
Gascon is a Romance dialect of the Occitan language traditionally spoken in southwestern France, particularly in the historical region of Gascony.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gascon Target entity description: Gascon is a Romance dialect of the Occitan language traditionally spoken in southwestern France, particularly in the historical region of Gascony.
-
A.
Breton
Breton is a Celtic language spoken primarily in Brittany, France, known for its close relation to Cornish and Welsh.
-
B.
Niçard Occitan
Niçard Occitan is a Romance variety of the Occitan language traditionally spoken in and around the city of Nice in southeastern France.
-
C.
Occitan
chosen
Occitan is a Romance language historically spoken in southern France and neighboring regions, known for its rich medieval literary tradition and close relation to Catalan.
-
D.
Haketia
Haketia is a Judeo-Spanish dialect historically spoken by Sephardic Jews in northern Morocco and parts of Gibraltar, characterized by strong influences from Moroccan Arabic and Hebrew.
-
E.
Jèrriais
Jèrriais is a Norman Romance language traditionally spoken on the island of Jersey in the Channel Islands.
- F. None of above.
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_69a4934c753c81909b309027e48b9b3a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a58fa41c819082de2cc4e0cb2943 |
completed | March 1, 2026, 8:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a79280fa5c819098397cc1b5c626c0 |
completed | March 4, 2026, 2:01 a.m. |
| NEDg | Description generation | batch_69a79329fc2c81908dbf0627686ef47e |
completed | March 4, 2026, 2:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a793b89e38819090fd80afbb0fee96 |
completed | March 4, 2026, 2:06 a.m. |
Created at: March 1, 2026, 7:37 p.m.