Triple
T2785888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jarnac |
E61808
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object |
Cognac
Cognac is a renowned French town in the Charente department, famous worldwide as the center of production for the eponymous brandy.
|
E300144
|
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: Cognac | Statement: [Jarnac, locatedNear, Cognac]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cognac Context triple: [Jarnac, locatedNear, Cognac]
-
A.
Armagnac
Armagnac is a historic French brandy-producing region renowned for its distinctive, long-aged eaux-de-vie made from local grapes.
-
B.
Calvados
Calvados is a department in the Normandy region of northwestern France, known for its historic D-Day landing beaches and production of the apple brandy that shares its name.
-
C.
Hennessy
Hennessy is a surname most prominently associated with John L. Hennessy, a renowned computer scientist and former president of Stanford University.
-
D.
Cider & Hennessy
Cider & Hennessy is a music release by American singer Jordin Sparks, showcasing her blend of R&B and pop influences.
-
E.
Bourbon-l’Archambault
Bourbon-l’Archambault is a historic spa town in central France known as the ancestral seat of the Bourbon dynasty.
- 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: Cognac Triple: [Jarnac, locatedNear, Cognac]
Generated description
Cognac is a renowned French town in the Charente department, famous worldwide as the center of production for the eponymous brandy.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Cognac Target entity description: Cognac is a renowned French town in the Charente department, famous worldwide as the center of production for the eponymous brandy.
-
A.
Armagnac
Armagnac is a historic French brandy-producing region renowned for its distinctive, long-aged eaux-de-vie made from local grapes.
-
B.
Calvados
Calvados is a department in the Normandy region of northwestern France, known for its historic D-Day landing beaches and production of the apple brandy that shares its name.
-
C.
Hennessy
Hennessy is a surname most prominently associated with John L. Hennessy, a renowned computer scientist and former president of Stanford University.
-
D.
Cider & Hennessy
Cider & Hennessy is a music release by American singer Jordin Sparks, showcasing her blend of R&B and pop influences.
-
E.
Bourbon-l’Archambault
Bourbon-l’Archambault is a historic spa town in central France known as the ancestral seat of the Bourbon dynasty.
- 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_69ab4b7f51d881908768300ebd2fbdae |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abddaf223c8190959bb0b336e5b7c0 |
completed | March 7, 2026, 8:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afc6526d0c81908df1710709cc5346 |
completed | March 10, 2026, 7:20 a.m. |
| NEDg | Description generation | batch_69afc852c0988190bba816db0940139f |
completed | March 10, 2026, 7:29 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69afc8b333848190bf4bfbc31f9c5147 |
completed | March 10, 2026, 7:30 a.m. |
Created at: March 6, 2026, 9:57 p.m.