Triple
T11887986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gare de Tours |
E282840
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Nantes |
E16517
|
NE FINISHED |
How this triple was built (2 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: Nantes | Statement: [Gare de Tours, connectsTo, Nantes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nantes Context triple: [Gare de Tours, connectsTo, Nantes]
-
A.
Nantes
chosen
Nantes is a historic port city in western France on the Loire River, known for its maritime heritage, cultural institutions, and vibrant arts scene.
-
B.
Rennes
Rennes is the capital city of France’s Brittany region, known for its historic medieval center, vibrant student population, and role as a major cultural and economic hub in western France.
-
C.
Clermont-Ferrand
Clermont-Ferrand is a central French city known for its historic cathedral built of black volcanic stone and as the longtime headquarters of the tire company Michelin.
-
D.
Rodez
Rodez is a historic cathedral city in southern France that serves as the capital of the Aveyron department in the Occitanie region.
-
E.
La Rochelle
La Rochelle is a historic French Atlantic port city that became a major stronghold and refuge for Huguenots during the French Wars of Religion.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6ab2a90b08190a4e818821cc93e6d |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8d3a2860c8190a21af5fcddbd2f1e |
completed | April 10, 2026, 10:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f49c7ab48c8190a7cf4e6be6aacc12 |
completed | May 1, 2026, 12:28 p.m. |
Created at: April 8, 2026, 9:44 p.m.