Triple
T2417301
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Garabit Viaduct |
E52334
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object |
Saint-Flour
Saint-Flour is a historic hilltop town in the Cantal department of south-central France, known for its medieval architecture and dramatic setting in the Auvergne region.
|
E284509
|
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: Saint-Flour | Statement: [Garabit Viaduct, locatedNear, Saint-Flour]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saint-Flour Context triple: [Garabit Viaduct, locatedNear, Saint-Flour]
-
A.
Yssingeaux
Yssingeaux is a commune in south-central France that serves as an administrative and service center in the Haute-Loire department.
-
B.
Thoiry
Thoiry is a commune in the Ain department of eastern France, located near the Swiss border in the Pays de Gex region.
-
C.
Oyonnax
Oyonnax is a town in eastern France’s Ain department, known historically for its plastics industry and its role in the French Resistance during World War II.
-
D.
Tournus
Tournus is a historic town in eastern France’s Burgundy region, known for its Romanesque abbey and riverside setting along the Saône.
-
E.
Olbreuse
Olbreuse is a small locality in western France historically notable as the ancestral seat of the noble d’Olbreuse family.
- 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: Saint-Flour Triple: [Garabit Viaduct, locatedNear, Saint-Flour]
Generated description
Saint-Flour is a historic hilltop town in the Cantal department of south-central France, known for its medieval architecture and dramatic setting in the Auvergne region.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Saint-Flour Target entity description: Saint-Flour is a historic hilltop town in the Cantal department of south-central France, known for its medieval architecture and dramatic setting in the Auvergne region.
-
A.
Yssingeaux
Yssingeaux is a commune in south-central France that serves as an administrative and service center in the Haute-Loire department.
-
B.
Thoiry
Thoiry is a commune in the Ain department of eastern France, located near the Swiss border in the Pays de Gex region.
-
C.
Oyonnax
Oyonnax is a town in eastern France’s Ain department, known historically for its plastics industry and its role in the French Resistance during World War II.
-
D.
Tournus
Tournus is a historic town in eastern France’s Burgundy region, known for its Romanesque abbey and riverside setting along the Saône.
-
E.
Olbreuse
Olbreuse is a small locality in western France historically notable as the ancestral seat of the noble d’Olbreuse family.
- 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_69ab495622948190bc6bc6e4cddaf645 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abc94eafd481909eeff689e5bf5960 |
completed | March 7, 2026, 6:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af9060a6b88190b80e5fb0970957e1 |
completed | March 10, 2026, 3:30 a.m. |
| NEDg | Description generation | batch_69af91c6de008190ad8fb3a3c06472cb |
completed | March 10, 2026, 3:36 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69af92500920819082c651f75a06dd72 |
completed | March 10, 2026, 3:38 a.m. |
Created at: March 6, 2026, 9:42 p.m.