Triple
T9472371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sundern |
E228422
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object |
Torcy
Torcy is a commune in France known for its twinning partnership with the German town of Sundern.
|
E809567
|
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: Torcy | Statement: [Sundern, hasTwinTown, Torcy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Torcy Context triple: [Sundern, hasTwinTown, Torcy]
-
A.
Bourgueil
Bourgueil is a Loire Valley wine appellation in France renowned for its red wines, particularly those made predominantly from Cabernet Franc.
-
B.
Chelles–Gournay
Chelles–Gournay is a suburban railway station in the eastern Paris metropolitan area that serves as the outer terminus of RER line E.
-
C.
Grigny
Grigny is a suburban commune in the southern outskirts of Paris, France, known for its large housing estates and diverse population.
-
D.
Plessis-lez-Tours
Plessis-lez-Tours is a historic former royal residence near Tours in central France, best known as the place where King Louis XI died.
-
E.
Chevry
Chevry is a small French commune located in eastern France within the Ain department, near the Swiss border and the city of Geneva.
- 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: Torcy Triple: [Sundern, hasTwinTown, Torcy]
Generated description
Torcy is a commune in France known for its twinning partnership with the German town of Sundern.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Torcy Target entity description: Torcy is a commune in France known for its twinning partnership with the German town of Sundern.
-
A.
Bourgueil
Bourgueil is a Loire Valley wine appellation in France renowned for its red wines, particularly those made predominantly from Cabernet Franc.
-
B.
Chelles–Gournay
Chelles–Gournay is a suburban railway station in the eastern Paris metropolitan area that serves as the outer terminus of RER line E.
-
C.
Grigny
Grigny is a suburban commune in the southern outskirts of Paris, France, known for its large housing estates and diverse population.
-
D.
Plessis-lez-Tours
Plessis-lez-Tours is a historic former royal residence near Tours in central France, best known as the place where King Louis XI died.
-
E.
Chevry
Chevry is a small French commune located in eastern France within the Ain department, near the Swiss border and the city of Geneva.
- 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_69ca847162c48190b079076c9595513c |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7fef6f288190b2d158c829b31de9 |
completed | April 1, 2026, 8:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d178e38d488190a4bc594b12a44baf |
completed | April 4, 2026, 8:47 p.m. |
| NEDg | Description generation | batch_69d179a4006c81909e983559b5fd7698 |
completed | April 4, 2026, 8:50 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d17a3aebfc8190acbe62ac900dd9e7 |
completed | April 4, 2026, 8:53 p.m. |
Created at: March 30, 2026, 7:54 p.m.