Triple
T23322085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tokachi region |
E591178
|
entity |
| Predicate | knownFor |
P22
|
FINISHED |
| Object | Tokachi milk |
—
|
NE NERFINISHED |
How this triple was built (2 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: Tokachi milk | Statement: [Tokachi region, knownFor, Tokachi milk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tokachi milk Context triple: [Tokachi region, knownFor, Tokachi milk]
-
A.
Moloko
Moloko was a British electronic music duo known for their eclectic blend of trip hop, dance, and pop, and for hits like "Sing It Back" and "The Time Is Now."
-
B.
Sanka
Sanka is a well-known brand of decaffeinated coffee that became popular in the United States during the 20th century.
-
C.
Wazuka
Wazuka is a rural town in Kyoto Prefecture, Japan, renowned for its historic tea fields and high-quality Uji tea production.
-
D.
Milk
Milk is a 2008 biographical film about gay rights activist and politician Harvey Milk, directed by Gus Van Sant and starring Sean Penn.
-
E.
Milk
chosen
Milk is a nutrient-rich white liquid produced by the mammary glands of mammals and widely consumed as a staple food and beverage by humans.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e25d1effe4819096907f95f610dbff |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1978672148190bb90804361bb896b |
completed | April 29, 2026, 5:30 a.m. |
Created at: April 17, 2026, 5:07 p.m.