Triple
T18753905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 林 |
E458596
|
entity |
| Predicate | kunYomiJapanese |
P52970
|
FINISHED |
| Object | はやし (hayashi) |
—
|
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: はやし (hayashi) | Statement: [林, kunYomiJapanese, はやし (hayashi)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: kunYomiJapanese Context triple: [林, kunYomiJapanese, はやし (hayashi)]
-
A.
japaneseKunReading
chosen
Indicates that a Japanese kanji character has a specific native Japanese (kun) reading associated with it.
-
B.
kun’yomiDerivedFrom
Indicates that a Japanese kun’yomi (native Japanese reading of a kanji) originates from or is historically derived from another form, source, or expression.
-
C.
kanji
Indicates that an entity is written in, represented by, or associated with a specific kanji character or set of kanji characters.
-
D.
typicalKanjiSpelling
Indicates that one written form is the standard or most commonly used kanji spelling for another expression (such as a word or phrase).
-
E.
componentKanji2
Indicates that one kanji character serves as the second component or sub-part of another kanji.
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e579ef4ee48190a9892ac9787ffe37 |
completed | April 20, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69e48d0b7b708190877951b6e6cdcbc4 |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:51 a.m.