Triple
T3711074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | hitsumabushi |
E81410
|
entity |
| Predicate | eatingCustom |
P7171
|
FINISHED |
| Object | dividing rice and eel into several portions |
—
|
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: dividing rice and eel into several portions | Statement: [hitsumabushi, eatingCustom, dividing rice and eel into several portions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eatingCustom Context triple: [hitsumabushi, eatingCustom, dividing rice and eel into several portions]
-
A.
foodCustom
chosen
Indicates a culturally specific practice, rule, or tradition related to the preparation, serving, or consumption of food.
-
B.
alsoEats
Indicates that an entity consumes something in addition to another item or items it already eats.
-
C.
eatingPermitted
Indicates that an entity is allowed or authorized to eat in a given context or situation.
-
D.
eatenAs
Indicates that one entity is consumed or used as food by another entity.
-
E.
dietaryOptions
Indicates the types of diets or food-related preferences, restrictions, or choices that are applicable to or offered for an entity.
- 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_69ad8b1a81588190b3f27a5483bb610e |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adc584b86c8190ba1a1073da440b07 |
completed | March 8, 2026, 6:52 p.m. |
| PD | Predicate disambiguation | batch_69adc041a8608190a2d543dab6d2ef6c |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:33 p.m.