Triple
T12623311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greene King beer |
E301444
|
entity |
| Predicate | notableProduct |
P1448
|
FINISHED |
| Object |
Abbot Ale
Abbot Ale is a traditional English premium bitter ale brewed by Greene King, known for its rich malty character and balanced hop bitterness.
|
E995940
|
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: Abbot Ale | Statement: [Greene King beer, notableProduct, Abbot Ale]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abbot Ale Context triple: [Greene King beer, notableProduct, Abbot Ale]
-
A.
Burton ale
Burton ale is a traditional strong, malty English beer style historically associated with the brewing town of Burton upon Trent.
-
B.
Ballantine Ale
Ballantine Ale is a historic American beer brand known for its distinctive three-ring logo and long-standing presence in the U.S. brewing industry.
-
C.
Ales
Ales is the given name of Ales Bialiatski, a prominent Belarusian human rights activist and Nobel Peace Prize laureate.
-
D.
Bintang Beer
Bintang Beer is a popular Indonesian pale lager, often associated with the country’s major beer brand and widely consumed by locals and tourists alike.
-
E.
Zorok Beer
Zorok Beer is a lager brand produced by Asia Pacific Breweries, known for its easy-drinking taste and presence in several Asian markets.
- 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: Abbot Ale Triple: [Greene King beer, notableProduct, Abbot Ale]
Generated description
Abbot Ale is a traditional English premium bitter ale brewed by Greene King, known for its rich malty character and balanced hop bitterness.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Abbot Ale Target entity description: Abbot Ale is a traditional English premium bitter ale brewed by Greene King, known for its rich malty character and balanced hop bitterness.
-
A.
Burton ale
Burton ale is a traditional strong, malty English beer style historically associated with the brewing town of Burton upon Trent.
-
B.
Ballantine Ale
Ballantine Ale is a historic American beer brand known for its distinctive three-ring logo and long-standing presence in the U.S. brewing industry.
-
C.
Ales
Ales is the given name of Ales Bialiatski, a prominent Belarusian human rights activist and Nobel Peace Prize laureate.
-
D.
Bintang Beer
Bintang Beer is a popular Indonesian pale lager, often associated with the country’s major beer brand and widely consumed by locals and tourists alike.
-
E.
Zorok Beer
Zorok Beer is a lager brand produced by Asia Pacific Breweries, known for its easy-drinking taste and presence in several Asian markets.
- 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_69d7bdeaf49c8190b13800111fa77ea3 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d960c8671881909a102d28b0e7f603 |
completed | April 10, 2026, 8:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6686d770881909850ffaf820171d9 |
completed | May 2, 2026, 9:11 p.m. |
| NEDg | Description generation | batch_69f66a232cec81909846400f8725aede |
completed | May 2, 2026, 9:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f66b18e68881908bf79ab52bcc909e |
completed | May 2, 2026, 9:22 p.m. |
Created at: April 9, 2026, 5:14 p.m.