Triple
T20439344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Civray |
E501340
|
entity |
| Predicate | hasDemonym |
P191
|
FINISHED |
| Object |
Civraisien
Civraisien is the French demonym for inhabitants of the town of Civray in western France.
|
E1430735
|
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: Civraisien | Statement: [Civray, hasDemonym, Civraisien]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Civraisien Context triple: [Civray, hasDemonym, Civraisien]
-
A.
Raverdinois
Raverdinois are the inhabitants or natives of the commune of Varreddes in France.
-
B.
Morisyen
Morisyen is the French-based Creole language widely spoken in Mauritius and used as a key marker of the island’s national identity.
-
C.
Valentinois
Valentinois are the inhabitants or natives of Valence, a city in the Drôme department of southeastern France.
-
D.
Berrichon dialect
The Berrichon dialect is a regional variety of French traditionally spoken in the Berry region of central France, reflecting its distinct rural and historical linguistic heritage.
-
E.
Breton
Breton is a Celtic language spoken primarily in Brittany, France, known for its close relation to Cornish and Welsh.
- 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: Civraisien Triple: [Civray, hasDemonym, Civraisien]
Generated description
Civraisien is the French demonym for inhabitants of the town of Civray in western France.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Civraisien Target entity description: Civraisien is the French demonym for inhabitants of the town of Civray in western France.
-
A.
Raverdinois
Raverdinois are the inhabitants or natives of the commune of Varreddes in France.
-
B.
Morisyen
Morisyen is the French-based Creole language widely spoken in Mauritius and used as a key marker of the island’s national identity.
-
C.
Valentinois
Valentinois are the inhabitants or natives of Valence, a city in the Drôme department of southeastern France.
-
D.
Berrichon dialect
The Berrichon dialect is a regional variety of French traditionally spoken in the Berry region of central France, reflecting its distinct rural and historical linguistic heritage.
-
E.
Breton
Breton is a Celtic language spoken primarily in Brittany, France, known for its close relation to Cornish and Welsh.
- 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_69e0b4ab3cfc8190ac9bf32e932316b1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e685f112e48190a3af818c0f6ee839 |
completed | April 20, 2026, 8 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0883fd1af88190a34aef615ec3a23e |
completed | May 16, 2026, 2:49 p.m. |
| NEDg | Description generation | batch_6a0884d316148190b1fe155fc2dfbb7b |
completed | May 16, 2026, 2:53 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a088565cbcc81909b4bbc286d272ef6 |
completed | May 16, 2026, 2:55 p.m. |
Created at: April 16, 2026, 11:31 a.m.