Triple
T22516492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Strongbow |
E556660
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object |
Strongbow Cloudy Apple
Strongbow Cloudy Apple is a lightly sparkling apple cider known for its hazy appearance and smooth, refreshing taste.
|
E1539850
|
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: Strongbow Cloudy Apple | Statement: [Strongbow, hasVariant, Strongbow Cloudy Apple]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Strongbow Cloudy Apple Context triple: [Strongbow, hasVariant, Strongbow Cloudy Apple]
-
A.
Strongbow Dark Fruit
Strongbow Dark Fruit is a popular fruit-flavoured cider known for its sweet, berry-forward taste and deep, dark colour.
-
B.
Strongbow Pear
Strongbow Pear is a pear-flavoured variant of the Strongbow cider brand, offering a sweeter, fruitier alternative to its traditional apple cider.
-
C.
Strongbow Original
Strongbow Original is a flagship dry apple cider known for its crisp, refreshing taste and wide availability in pubs and stores.
-
D.
Strongbow Rosé
Strongbow Rosé is a fruit-flavoured rosé-style cider known for its light, refreshing taste and pink hue, produced under the Strongbow cider brand.
-
E.
Redd’s Apple Ale
Redd’s Apple Ale is a fruit-flavored alcoholic beverage known for its crisp, sweet apple taste and beer-like character.
- 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: Strongbow Cloudy Apple Triple: [Strongbow, hasVariant, Strongbow Cloudy Apple]
Generated description
Strongbow Cloudy Apple is a lightly sparkling apple cider known for its hazy appearance and smooth, refreshing taste.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Strongbow Cloudy Apple Target entity description: Strongbow Cloudy Apple is a lightly sparkling apple cider known for its hazy appearance and smooth, refreshing taste.
-
A.
Strongbow Dark Fruit
Strongbow Dark Fruit is a popular fruit-flavoured cider known for its sweet, berry-forward taste and deep, dark colour.
-
B.
Strongbow Pear
Strongbow Pear is a pear-flavoured variant of the Strongbow cider brand, offering a sweeter, fruitier alternative to its traditional apple cider.
-
C.
Strongbow Original
Strongbow Original is a flagship dry apple cider known for its crisp, refreshing taste and wide availability in pubs and stores.
-
D.
Strongbow Rosé
Strongbow Rosé is a fruit-flavoured rosé-style cider known for its light, refreshing taste and pink hue, produced under the Strongbow cider brand.
-
E.
Redd’s Apple Ale
Redd’s Apple Ale is a fruit-flavored alcoholic beverage known for its crisp, sweet apple taste and beer-like character.
- 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_69e11e5657e881909f16ca58352c50da |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15e2df59c81909c4ae2f20f1cbb32 |
completed | April 29, 2026, 1:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b17f152848190b4c8dc77596d625d |
completed | May 18, 2026, 1:45 p.m. |
| NEDg | Description generation | batch_6a0b1842c7208190801bce8d6fdb2bca |
completed | May 18, 2026, 1:46 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b1910f4a8819081644157406c523f |
completed | May 18, 2026, 1:50 p.m. |
Created at: April 16, 2026, 8:50 p.m.