Triple
T32500655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 雅幸 |
E830648
|
entity |
| Predicate | meaningComponentOfKanji幸 |
P174997
|
FINISHED |
| Object | good fortune |
—
|
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: good fortune | Statement: [雅幸, meaningComponentOfKanji幸, good fortune]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: meaningComponentOfKanji幸 Context triple: [雅幸, meaningComponentOfKanji幸, good fortune]
-
A.
meaningComponent幸
chosen
Indicates that the entity functions as a semantic or meaning-bearing component within a larger composite expression or structure.
-
B.
componentKanji1Meaning
Indicates that the first kanji component of a character corresponds to a particular meaning or semantic value.
-
C.
componentKanji2
Indicates that one kanji character serves as the second component or sub-part of another kanji.
-
D.
commonKanjiComponent
Indicates that two or more kanji share a common graphical component or radical in their written form.
-
E.
meaningOfKanji司
Indicates that one entity represents or explains the meaning or semantic content of the kanji character 司.
- 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_69f349219cb8819087e120f509629c1b |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6d74b20a48190900dda1014cc13a8 |
completed | May 3, 2026, 5:04 a.m. |
| PD | Predicate disambiguation | batch_69f6d26f27dc8190ae426a3e1573933e |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 12:59 a.m.