Triple
T19007069
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | canton of Ussel |
E465114
|
entity |
| Predicate | containsAdministrativeTerritorialEntity |
P747
|
FINISHED |
| Object |
Saint-Angel
Saint-Angel is a small French commune located in central France’s Corrèze department within the canton of Ussel.
|
E1353898
|
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: Saint-Angel | Statement: [canton of Ussel, containsAdministrativeTerritorialEntity, Saint-Angel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saint-Angel Context triple: [canton of Ussel, containsAdministrativeTerritorialEntity, Saint-Angel]
-
A.
Santángelo
Santángelo is a place in Spain historically associated with the noble title of Duke of Santángelo.
-
B.
Santa Rosa de Sacco
Santa Rosa de Sacco is a town in central Peru located in the Andean highlands of the Junín region.
-
C.
Belmonte
Belmonte is a historic town in Portugal known for its medieval castle and strong Jewish heritage, located in the country's Centro Region.
-
D.
Arichat
Arichat is a historic coastal village on Isle Madame in Nova Scotia, Canada, known for its Acadian heritage and long-standing fishing and maritime traditions.
-
E.
San Cosme
San Cosme is a Mexico City Metro station on Line 2 that serves the San Rafael neighborhood near the historic center of the city.
- 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: Saint-Angel Triple: [canton of Ussel, containsAdministrativeTerritorialEntity, Saint-Angel]
Generated description
Saint-Angel is a small French commune located in central France’s Corrèze department within the canton of Ussel.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Saint-Angel Target entity description: Saint-Angel is a small French commune located in central France’s Corrèze department within the canton of Ussel.
-
A.
Santángelo
Santángelo is a place in Spain historically associated with the noble title of Duke of Santángelo.
-
B.
Santa Rosa de Sacco
Santa Rosa de Sacco is a town in central Peru located in the Andean highlands of the Junín region.
-
C.
Belmonte
Belmonte is a historic town in Portugal known for its medieval castle and strong Jewish heritage, located in the country's Centro Region.
-
D.
Arichat
Arichat is a historic coastal village on Isle Madame in Nova Scotia, Canada, known for its Acadian heritage and long-standing fishing and maritime traditions.
-
E.
San Cosme
San Cosme is a Mexico City Metro station on Line 2 that serves the San Rafael neighborhood near the historic center of the city.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6a561848190bd957f248471c191 |
completed | April 20, 2026, 7:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05b463d4a08190b15403ea0ad23682 |
completed | May 14, 2026, 11:39 a.m. |
| NEDg | Description generation | batch_6a05b5dfac0c8190b67921280d5ab1fe |
completed | May 14, 2026, 11:45 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a05b68aba3081908ca21d732e45f454 |
completed | May 14, 2026, 11:48 a.m. |
Created at: April 10, 2026, 12:01 p.m.