Triple
T8054284
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Setsubun |
E187755
|
entity |
| Predicate | ehomakiCustom |
P80783
|
FINISHED |
| Object | eating a thick sushi roll while facing the lucky direction |
—
|
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: eating a thick sushi roll while facing the lucky direction | Statement: [Setsubun, ehomakiCustom, eating a thick sushi roll while facing the lucky direction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ehomakiCustom Context triple: [Setsubun, ehomakiCustom, eating a thick sushi roll while facing the lucky direction]
-
A.
isOftenHomemade
Indicates that something is frequently made at home rather than being purchased or produced commercially.
-
B.
hokkienTeochewForm
Indicates that one entity is the Hokkien/Teochew linguistic form or variant corresponding to another entity.
-
C.
isTypicallyGarnishedWith
Indicates that one item is commonly used as a garnish or decorative finishing element for another.
-
D.
eggGroup
Indicates the breeding compatibility category or group to which an organism belongs.
-
E.
haveCuisine
Indicates that an entity (such as a restaurant or place) offers, serves, or is associated with a particular type or style of cuisine.
- F. None of above. chosen
Provenance (4 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_69ca82b15e948190a62fd7af5218426a |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3f9fb8dc8190bacc1f66ddfd1cbf |
completed | March 31, 2026, 3:29 a.m. |
| PD | Predicate disambiguation | batch_69cb049a1b9c8190811c396421ebf9c9 |
completed | March 30, 2026, 11:17 p.m. |
| PDg | Predicate description generation | batch_69cb14bcbbc0819094a98e7ffffb7a40 |
completed | March 31, 2026, 12:26 a.m. |
Created at: March 30, 2026, 5:25 p.m.