Triple
T23362496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | arrondissement of Vannes |
E593220
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Billiers
Billiers is a small coastal commune in the Morbihan department of Brittany in northwestern France.
|
E1584682
|
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: Billiers | Statement: [arrondissement of Vannes, contains, Billiers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Billiers Context triple: [arrondissement of Vannes, contains, Billiers]
-
A.
Biljarda
Biljarda is a historic building in Cetinje, Montenegro, best known as the former residence of Petar II Petrović-Njegoš and now home to the National Museum of Montenegro.
-
B.
de la Billière
De la Billière is the surname of Sir Peter de la Billière, a prominent British Army general best known for commanding UK forces during the 1991 Gulf War.
-
C.
Sinai billiards
Sinai billiards is a mathematical model in dynamical systems theory that studies the chaotic motion of a point particle reflecting elastically inside a planar domain with convex scatterers.
-
D.
Baize
The Baize is a river in northwestern France that flows through the Normandy region as a tributary of the Orne.
-
E.
Nine Ball
Nine Ball is a savvy, dreadlocked hacker played by Rihanna in the heist film "Ocean's 8."
- 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: Billiers Triple: [arrondissement of Vannes, contains, Billiers]
Generated description
Billiers is a small coastal commune in the Morbihan department of Brittany in northwestern France.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Billiers Target entity description: Billiers is a small coastal commune in the Morbihan department of Brittany in northwestern France.
-
A.
Biljarda
Biljarda is a historic building in Cetinje, Montenegro, best known as the former residence of Petar II Petrović-Njegoš and now home to the National Museum of Montenegro.
-
B.
de la Billière
De la Billière is the surname of Sir Peter de la Billière, a prominent British Army general best known for commanding UK forces during the 1991 Gulf War.
-
C.
Sinai billiards
Sinai billiards is a mathematical model in dynamical systems theory that studies the chaotic motion of a point particle reflecting elastically inside a planar domain with convex scatterers.
-
D.
Baize
The Baize is a river in northwestern France that flows through the Normandy region as a tributary of the Orne.
-
E.
Nine Ball
Nine Ball is a savvy, dreadlocked hacker played by Rihanna in the heist film "Ocean's 8."
- 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_69e25d2593c88190bcdf4a716a94ccb2 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a0aa0ed88190b0198cbfd1bcc59b |
completed | April 29, 2026, 6:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c5dd5ca4881909453c262d6ab9b1a |
completed | May 19, 2026, 12:55 p.m. |
| NEDg | Description generation | batch_6a0c61cdf14481909173cc65e16f2c82 |
completed | May 19, 2026, 1:12 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c625b52248190ba3d59f42dd99da3 |
completed | May 19, 2026, 1:15 p.m. |
Created at: April 17, 2026, 5:30 p.m.