Triple
T16801911
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treasury Wine Estates |
E408376
|
entity |
| Predicate | ownsBrand |
P1500
|
FINISHED |
| Object |
Seppelt
Seppelt is a historic Australian wine producer renowned for its sparkling wines and extensive underground cellars.
|
E1232954
|
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: Seppelt | Statement: [Treasury Wine Estates, ownsBrand, Seppelt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Seppelt Context triple: [Treasury Wine Estates, ownsBrand, Seppelt]
-
A.
Arlac
Arlac is a district in the city of Mérignac, near Bordeaux in southwestern France, known for its residential character and proximity to notable historic sites.
-
B.
Steenberg
Steenberg is a suburb in Cape Town, South Africa, situated near the Pollsmoor maximum-security prison.
-
C.
Aidells
Aidells is a specialty sausage and meat brand known for its gourmet, flavor-forward products made with premium ingredients.
-
D.
Hauerland
Hauerland was a historical German-speaking enclave in central Slovakia, settled by Carpathian Germans in the Middle Ages.
-
E.
Seelbach
Seelbach is a municipality in southwestern Germany’s Baden-Württemberg region, situated in the Ortenau district near the Black Forest.
- 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: Seppelt Triple: [Treasury Wine Estates, ownsBrand, Seppelt]
Generated description
Seppelt is a historic Australian wine producer renowned for its sparkling wines and extensive underground cellars.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Seppelt Target entity description: Seppelt is a historic Australian wine producer renowned for its sparkling wines and extensive underground cellars.
-
A.
Arlac
Arlac is a district in the city of Mérignac, near Bordeaux in southwestern France, known for its residential character and proximity to notable historic sites.
-
B.
Steenberg
Steenberg is a suburb in Cape Town, South Africa, situated near the Pollsmoor maximum-security prison.
-
C.
Aidells
Aidells is a specialty sausage and meat brand known for its gourmet, flavor-forward products made with premium ingredients.
-
D.
Hauerland
Hauerland was a historical German-speaking enclave in central Slovakia, settled by Carpathian Germans in the Middle Ages.
-
E.
Seelbach
Seelbach is a municipality in southwestern Germany’s Baden-Württemberg region, situated in the Ortenau district near the Black Forest.
- 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_69d88393905081908d00a86b99996ac8 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3b2c8fe58819087d3b83635255c34 |
completed | April 18, 2026, 4:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00ab1598dc81909fa5118e739a3291 |
completed | May 10, 2026, 3:58 p.m. |
| NEDg | Description generation | batch_6a00ab7a9b448190bdaf460bbe5f8c2b |
completed | May 10, 2026, 3:59 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00abf09fe4819082ee0c6c6f702822 |
completed | May 10, 2026, 4:01 p.m. |
Created at: April 10, 2026, 5:22 a.m.