Triple
T8054283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Setsubun |
E187755
|
entity |
| Predicate | ehomakiMeaning |
P75337
|
FINISHED |
| Object | lucky direction sushi roll |
—
|
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: lucky direction sushi roll | Statement: [Setsubun, ehomakiMeaning, lucky direction sushi roll]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ehomakiMeaning Context triple: [Setsubun, ehomakiMeaning, lucky direction sushi roll]
-
A.
typicalKanjiMeaning
Indicates that one entity is the standard or commonly accepted meaning associated with a given kanji character.
-
B.
ermenMeaning
chosen
Indicates that one entity represents or conveys the meaning or semantic interpretation of another entity.
-
C.
PSEMeaning
Indicates that one entity expresses, conveys, or encodes a particular meaning or semantic content in relation to another.
-
D.
handMeaning
Indicates that one entity uses or positions its hand in a particular way to convey a specific meaning, message, or communicative intent toward another entity.
-
E.
KTMMeaning
Indicates that an entity represents or conveys the meaning, definition, or semantic interpretation associated with the term or concept "KTM."
- 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_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. |
Created at: March 30, 2026, 5:25 p.m.