Triple
T30441738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 天神川 |
E774462
|
entity |
| Predicate | 漢字表記 |
P155698
|
FINISHED |
| Object | 天神川 |
—
|
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: 天神川 | Statement: [天神川, 漢字表記, 天神川]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 漢字表記 Context triple: [天神川, 漢字表記, 天神川]
-
A.
別表記
Indicates that one entity is an alternative written form or spelling variant of another entity.
-
B.
hanjaName
Indicates that one entity is the Sino-Korean (hanja) written form corresponding to the name of another entity.
-
C.
hasTraditionalCharacter
Indicates that an entity is associated with or represented by a traditional (non-simplified or historically established) written character form.
-
D.
usesHanjaVariants
Indicates that one entity employs or incorporates alternative Hanja (Chinese character) forms corresponding to another entity.
-
E.
termInJapaneseScript
chosen
Indicates that a given term is written or represented using Japanese script (such as kanji, hiragana, or katakana).
- 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_69f22493ef9c8190ae8c2afcb7f994c8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6869948e481908901dbda23952cc0 |
completed | May 2, 2026, 11:19 p.m. |
| PD | Predicate disambiguation | batch_69f678d2196c8190b9d0d2fcd47cc539 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 29, 2026, 8:08 p.m.