Triple
T18919047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arrondissement of Avranches |
E462796
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Carolles
Carolles is a small coastal commune in the Manche department of northwestern France, known for its scenic cliffs and beaches along the English Channel.
|
E1349925
|
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: Carolles | Statement: [Arrondissement of Avranches, contains, Carolles]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carolles Context triple: [Arrondissement of Avranches, contains, Carolles]
-
A.
Glavieux
Glavieux is a French surname most notably associated with Alain Glavieux, a prominent engineer known for his contributions to error-correcting codes.
-
B.
Bonaly
Bonaly is a small residential and recreational area on the southwestern edge of Edinburgh, Scotland, known for its proximity to the Pentland Hills and outdoor activities.
-
C.
Bonaly
Bonaly is the surname of French figure skater Surya Bonaly, renowned for her powerful athleticism and signature backflip on ice.
-
D.
Courcier
Courcier was a French publishing house known for issuing important mathematical and scientific works in the early 19th century.
-
E.
Deauzya
Deauzya is the given first name of American professional basketball player DiDi Richards.
- 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: Carolles Triple: [Arrondissement of Avranches, contains, Carolles]
Generated description
Carolles is a small coastal commune in the Manche department of northwestern France, known for its scenic cliffs and beaches along the English Channel.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Carolles Target entity description: Carolles is a small coastal commune in the Manche department of northwestern France, known for its scenic cliffs and beaches along the English Channel.
-
A.
Glavieux
Glavieux is a French surname most notably associated with Alain Glavieux, a prominent engineer known for his contributions to error-correcting codes.
-
B.
Bonaly
Bonaly is a small residential and recreational area on the southwestern edge of Edinburgh, Scotland, known for its proximity to the Pentland Hills and outdoor activities.
-
C.
Bonaly
Bonaly is the surname of French figure skater Surya Bonaly, renowned for her powerful athleticism and signature backflip on ice.
-
D.
Courcier
Courcier was a French publishing house known for issuing important mathematical and scientific works in the early 19th century.
-
E.
Deauzya
Deauzya is the given first name of American professional basketball player DiDi Richards.
- 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_69d8dcfdbbb881909964fa5a75bd0b48 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c629527481909dad169f07df0da4 |
completed | April 20, 2026, 6:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0591165cbc8190a0aafbd6611c8095 |
completed | May 14, 2026, 9:08 a.m. |
| NEDg | Description generation | batch_6a05965ab9a081909e430d9bef63c820 |
completed | May 14, 2026, 9:31 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0596c2ee4c8190b3b4db9afa4d1bed |
completed | May 14, 2026, 9:32 a.m. |
Created at: April 10, 2026, 11:59 a.m.