Triple
T37999187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hiyajiru udon |
E948043
|
entity |
| Predicate | hasBrothType |
P67754
|
FINISHED |
| Object | sesame-based broth |
—
|
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: sesame-based broth | Statement: [Hiyajiru udon, hasBrothType, sesame-based broth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBrothType Context triple: [Hiyajiru udon, hasBrothType, sesame-based broth]
-
A.
typicalBrothType
Indicates the kind of broth that is most commonly or traditionally used as the base for a given dish or preparation.
-
B.
hasRoastType
Indicates that one entity is characterized by or associated with a specific roast type of another entity.
-
C.
brothCharacteristic
Indicates that one entity specifies a quality, feature, or attribute of a broth associated with another entity.
-
D.
hasDishType
Indicates that an item (such as a food or menu entry) is classified as belonging to a particular type of dish (e.g., appetizer, main course, dessert).
-
E.
brothBase
chosen
Indicates that one item serves as the primary liquid or stock foundation (broth base) used to prepare or flavor another.
- 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_69f76efa37088190be5416b7ef1ca275 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fce7671f108190bf3ebf54339068b5 |
completed | May 7, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69fce5b5a84c81908ac1b5b9f08d48d0 |
completed | May 7, 2026, 7:19 p.m. |
Created at: May 3, 2026, 4:20 p.m.