Triple
T10207321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | General Foods |
E242232
|
entity |
| Predicate | product |
P490
|
FINISHED |
| Object |
Sanka
Sanka is a well-known brand of decaffeinated coffee that became popular in the United States during the 20th century.
|
E849450
|
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: Sanka | Statement: [General Foods, product, Sanka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sanka Context triple: [General Foods, product, Sanka]
-
A.
Sanka Coffie
Sanka Coffie is the laid-back, humorous pushcart driver and brakeman who provides comic relief and heart in the Jamaican bobsled team in the film "Cool Runnings."
-
B.
Tarbock
Tarbock is a village in the Metropolitan Borough of Knowsley in Merseyside, England, known historically for its agricultural roots and rural character.
-
C.
Wazuka
Wazuka is a rural town in Kyoto Prefecture, Japan, renowned for its historic tea fields and high-quality Uji tea production.
-
D.
Hersey
Hersey is a surname most notably associated with John Hersey, the American writer and journalist renowned for his work "Hiroshima."
-
E.
Yamazaki Biscuits
Yamazaki Biscuits is a Japanese confectionery and snack manufacturer best known for producing a wide range of biscuits and cookies and for its long-standing involvement in sports sponsorships.
- 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: Sanka Triple: [General Foods, product, Sanka]
Generated description
Sanka is a well-known brand of decaffeinated coffee that became popular in the United States during the 20th century.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sanka Target entity description: Sanka is a well-known brand of decaffeinated coffee that became popular in the United States during the 20th century.
-
A.
Sanka Coffie
Sanka Coffie is the laid-back, humorous pushcart driver and brakeman who provides comic relief and heart in the Jamaican bobsled team in the film "Cool Runnings."
-
B.
Tarbock
Tarbock is a village in the Metropolitan Borough of Knowsley in Merseyside, England, known historically for its agricultural roots and rural character.
-
C.
Wazuka
Wazuka is a rural town in Kyoto Prefecture, Japan, renowned for its historic tea fields and high-quality Uji tea production.
-
D.
Hersey
Hersey is a surname most notably associated with John Hersey, the American writer and journalist renowned for his work "Hiroshima."
-
E.
Yamazaki Biscuits
Yamazaki Biscuits is a Japanese confectionery and snack manufacturer best known for producing a wide range of biscuits and cookies and for its long-standing involvement in sports sponsorships.
- 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_69d381ae26c48190985abd0e25ee5d04 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d395f8e2b881909c51f8210f09cd4f |
completed | April 6, 2026, 11:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d652c13d748190908d1869c60e84c3 |
completed | April 8, 2026, 1:06 p.m. |
| NEDg | Description generation | batch_69d653c9f3e48190a51f6c6285d55e1d |
completed | April 8, 2026, 1:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d65433b62081908895b50139b3de3f |
completed | April 8, 2026, 1:12 p.m. |
Created at: April 6, 2026, 10:56 a.m.