Triple
T14134641
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leysse River |
E350257
|
entity |
| Predicate | hasNameInLanguage |
P15
|
FINISHED |
| Object |
Leysse@fr
Leysse is a river in the Savoie department of southeastern France that flows through the city of Chambéry before joining the Lac du Bourget.
|
E1081829
|
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: Leysse@fr | Statement: [Leysse River, hasNameInLanguage, Leysse@fr]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leysse@fr Context triple: [Leysse River, hasNameInLanguage, Leysse@fr]
-
A.
Lez (French)
Lez (French) is the French name of the Lez River, a watercourse in southern France that flows through the city of Montpellier before reaching the Mediterranean Sea.
-
B.
Leyssins
Leyssins is a small river or stream associated with the area of Chambéry in southeastern France.
-
C.
Lesse
The Lesse is a scenic river in southern Belgium known for flowing through the Ardennes, its limestone caves, and popular kayaking routes.
-
D.
Lysse
Lysse is a fashion and apparel brand known for its stylish, comfortable leggings and women’s clothing.
-
E.
Léez
Léez is a river in southwestern France that serves as a tributary within the Gave de Pau river system.
- 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: Leysse@fr Triple: [Leysse River, hasNameInLanguage, Leysse@fr]
Generated description
Leysse is a river in the Savoie department of southeastern France that flows through the city of Chambéry before joining the Lac du Bourget.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Leysse@fr Target entity description: Leysse is a river in the Savoie department of southeastern France that flows through the city of Chambéry before joining the Lac du Bourget.
-
A.
Lez (French)
Lez (French) is the French name of the Lez River, a watercourse in southern France that flows through the city of Montpellier before reaching the Mediterranean Sea.
-
B.
Leyssins
Leyssins is a small river or stream associated with the area of Chambéry in southeastern France.
-
C.
Lesse
The Lesse is a scenic river in southern Belgium known for flowing through the Ardennes, its limestone caves, and popular kayaking routes.
-
D.
Lysse
Lysse is a fashion and apparel brand known for its stylish, comfortable leggings and women’s clothing.
-
E.
Léez
Léez is a river in southwestern France that serves as a tributary within the Gave de Pau river system.
- 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_69d827865f608190b311820428ae027b |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de610e949c8190852d336c9d12bfd0 |
completed | April 14, 2026, 3:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcdf14439c81908b2a9999a35cc346 |
completed | May 7, 2026, 6:51 p.m. |
| NEDg | Description generation | batch_69fce396360481909fe12fdee307d00d |
completed | May 7, 2026, 7:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fce3d07f048190833bd56b46a9f5fb |
completed | May 7, 2026, 7:11 p.m. |
Created at: April 9, 2026, 11:57 p.m.