Triple
T16681196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ai (Chinese surname) |
E405341
|
entity |
| Predicate | transliterationToKoreanHangul |
P52969
|
FINISHED |
| Object | 애 |
—
|
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: 애 | Statement: [Ai (Chinese surname), transliterationToKoreanHangul, 애]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transliterationToKoreanHangul Context triple: [Ai (Chinese surname), transliterationToKoreanHangul, 애]
-
A.
hangulNameRomanized
Indicates that an entity’s Korean Hangul name is represented in its romanized (Latin alphabet) form.
-
B.
koreanReadingHangul
chosen
Indicates that an entity’s Korean reading is represented in Hangul script.
-
C.
transliterationTarget
Indicates that one entity is the target script or form into which another entity is transliterated.
-
D.
formerTransliteration
Indicates that one transliteration was previously used for an entity but has since been replaced by a different transliteration.
-
E.
typicalTransliterationFrom
Indicates that one string is the standard or most commonly used transliteration of another string from one writing system to another.
- 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_69d8838c28748190b3f5967c743940ab |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37d6f5cf481909e7628bbaa884e5a |
completed | April 18, 2026, 12:47 p.m. |
| PD | Predicate disambiguation | batch_69e319bc73908190a0e38bc926b31f10 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:19 a.m.