Triple
T17646274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wanko Soba |
E429365
|
entity |
| Predicate | etiquette |
P97883
|
FINISHED |
| Object | keep eating as long as bowl is refilled |
—
|
LITERAL FINISHED |
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: keep eating as long as bowl is refilled | Statement: [Wanko Soba, etiquette, keep eating as long as bowl is refilled]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: etiquette Context triple: [Wanko Soba, etiquette, keep eating as long as bowl is refilled]
-
A.
politenessLevel
Indicates the degree of courteousness or respectfulness expressed by one entity toward another in an interaction.
-
B.
decorum
chosen
Indicates adherence to socially accepted standards of proper, polite, or appropriate behavior in a given context.
-
C.
hasManner
Indicates the way, style, or method in which an action is performed or a relation is carried out.
-
D.
honorificUse
Indicates that one entity refers to or addresses another using an honorific title or respectful linguistic form.
-
E.
regards
Indicates that one entity considers, views, or treats another entity in a particular way or with a certain attitude.
- F. None of above.
Provenance (3 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_69d889e2c2608190b762e76d9b2262f1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46e39937881909bb6a1792fff39a9 |
completed | April 19, 2026, 5:55 a.m. |
| PD | Predicate disambiguation | batch_69e3cddc87188190ac2f049b86038676 |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 6:04 a.m.