Triple
T3931115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castelsarrasin |
E90795
|
entity |
| Predicate | sharesBorderWith |
P224
|
FINISHED |
| Object |
Angeville
Angeville is a small commune in the Tarn-et-Garonne department in southern France.
|
E399430
|
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: Angeville | Statement: [Castelsarrasin, sharesBorderWith, Angeville]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Angeville Context triple: [Castelsarrasin, sharesBorderWith, Angeville]
-
A.
Coutances
Coutances is a historic town in northwestern France known for its Gothic cathedral and role as an administrative and cultural center in the Manche department of Normandy.
-
B.
Dreux
Dreux is a historic town in northern France known for its royal chapel and role as a regional center in the Eure-et-Loir department.
-
C.
Langeac
Langeac is a small commune in south-central France, situated in the Haute-Loire department within the Auvergne-Rhône-Alpes region.
-
D.
Avranches
Avranches is a historic town in northwestern France, near Mont-Saint-Michel, known for its medieval heritage and role in the liberation of Normandy during World War II.
-
E.
Montargis
Montargis is a historic market town in north-central France, known for its canals, medieval architecture, and traditional praline confectionery.
- 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: Angeville Triple: [Castelsarrasin, sharesBorderWith, Angeville]
Generated description
Angeville is a small commune in the Tarn-et-Garonne department in southern France.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Angeville Target entity description: Angeville is a small commune in the Tarn-et-Garonne department in southern France.
-
A.
Coutances
Coutances is a historic town in northwestern France known for its Gothic cathedral and role as an administrative and cultural center in the Manche department of Normandy.
-
B.
Dreux
Dreux is a historic town in northern France known for its royal chapel and role as a regional center in the Eure-et-Loir department.
-
C.
Langeac
Langeac is a small commune in south-central France, situated in the Haute-Loire department within the Auvergne-Rhône-Alpes region.
-
D.
Avranches
Avranches is a historic town in northwestern France, near Mont-Saint-Michel, known for its medieval heritage and role in the liberation of Normandy during World War II.
-
E.
Montargis
Montargis is a historic market town in north-central France, known for its canals, medieval architecture, and traditional praline confectionery.
- 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_69aed95f26e0819094b0e71974543a19 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeeda98058819094dd6ab223670860 |
completed | March 9, 2026, 3:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5288408f0819090217513e7a21091 |
completed | March 14, 2026, 9:21 a.m. |
| NEDg | Description generation | batch_69b5294a9b80819083124bc2ff6828aa |
completed | March 14, 2026, 9:24 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b529f6a3488190a7a9ae37f71cff56 |
completed | March 14, 2026, 9:27 a.m. |
Created at: March 9, 2026, 3:23 p.m.