Triple
T105542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kanji |
E2128
|
entity |
| Predicate | on’yomiDerivedFrom |
P453
|
FINISHED |
| Object | Chinese pronunciation |
—
|
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: Chinese pronunciation | Statement: [Kanji, on’yomiDerivedFrom, Chinese pronunciation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: on’yomiDerivedFrom Context triple: [Kanji, on’yomiDerivedFrom, Chinese pronunciation]
-
A.
hasRomanizationOf
Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
-
B.
etymologyType
Indicates the specific kind or category of etymological relationship that links a term to its linguistic origin or source.
-
C.
hasEndonym
Indicates that an entity has a name or designation used by native speakers or within its own local language or community.
-
D.
etymology
chosen
Indicates the historical origin and development of a word or term, including its source language and form.
-
E.
hasLanguageOfOrigin
Indicates that one entity has its origin or source in the language specified by another entity.
- 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_69a24e0a5b7c81908d52da08c60dabc4 |
completed | Feb. 28, 2026, 2:08 a.m. |
| NER | Named-entity recognition | batch_69a25711f6788190a22252ea3a3af394 |
completed | Feb. 28, 2026, 2:46 a.m. |
| PD | Predicate disambiguation | batch_69a2563be81c81908ccc5ed44edd6b8e |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:12 a.m.