Triple
T1297257
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Puy-de-Dôme |
E27681
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Riom
Riom is a historic town in central France known for its preserved medieval architecture and role as a former capital of the Auvergne region.
|
E174959
|
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: Riom | Statement: [Puy-de-Dôme, contains, Riom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Riom Context triple: [Puy-de-Dôme, contains, Riom]
-
A.
Marseille
Marseille is a historic Mediterranean port city in southern France known for its diverse culture, maritime heritage, and role as a major economic hub.
-
B.
Vichy
Vichy is a spa town in central France renowned for its thermal springs, health resorts, and role as the seat of the World War II Vichy regime.
-
C.
Toulon
Toulon is a major port city on France’s Mediterranean coast that serves as the principal base of the French Navy.
-
D.
Lyon
Lyon is a major city in east-central France known for its historical and architectural landmarks, gastronomy, and role as a key economic and cultural center.
-
E.
Cantona
Cantona is the surname of Eric Cantona, the iconic French footballer and actor best known for his influential spell at Manchester United in the 1990s.
- 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: Riom Triple: [Puy-de-Dôme, contains, Riom]
Generated description
Riom is a historic town in central France known for its preserved medieval architecture and role as a former capital of the Auvergne region.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Riom Target entity description: Riom is a historic town in central France known for its preserved medieval architecture and role as a former capital of the Auvergne region.
-
A.
Marseille
Marseille is a historic Mediterranean port city in southern France known for its diverse culture, maritime heritage, and role as a major economic hub.
-
B.
Vichy
Vichy is a spa town in central France renowned for its thermal springs, health resorts, and role as the seat of the World War II Vichy regime.
-
C.
Toulon
Toulon is a major port city on France’s Mediterranean coast that serves as the principal base of the French Navy.
-
D.
Lyon
Lyon is a major city in east-central France known for its historical and architectural landmarks, gastronomy, and role as a key economic and cultural center.
-
E.
Cantona
Cantona is the surname of Eric Cantona, the iconic French footballer and actor best known for his influential spell at Manchester United in the 1990s.
- 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_69a496d6682881909ba658f1c1e0e2b0 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c0f6bc90819094cad5d62550ea19 |
completed | March 1, 2026, 10:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad293872cc8190894581cff289627e |
completed | March 8, 2026, 7:46 a.m. |
| NEDg | Description generation | batch_69ad2cfb8c4c8190b47406be414850ab |
completed | March 8, 2026, 8:02 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad2ded1d548190b0c51c460a751017 |
completed | March 8, 2026, 8:06 a.m. |
Created at: March 1, 2026, 7:51 p.m.