Triple
T12986643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cheong |
E321784
|
entity |
| Predicate | transliterationType |
P107909
|
FINISHED |
| Object | dialect-based romanization |
—
|
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: dialect-based romanization | Statement: [Cheong, transliterationType, dialect-based romanization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transliterationType Context triple: [Cheong, transliterationType, dialect-based romanization]
-
A.
transliterationLanguage
Indicates the language whose writing system is used as the target when converting text from one script to another.
-
B.
transliterationTarget
Indicates that one entity is the target script or form into which another entity is transliterated.
-
C.
transliterationName
Indicates that one entity is the transliterated form of another entity’s name from one writing system into another.
-
D.
commonTransliterationSystem
Indicates that two or more written forms are derived using the same standardized system for converting text from one script to another.
-
E.
alternativeTransliteration
Indicates that one written form represents an alternative way of transliterating the same original text or name into another script or orthography.
- F. None of above. chosen
Provenance (4 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_69d8076479b8819090afce3591939cdf |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97f2a71a0819098bb6cf8a4b2208a |
completed | April 10, 2026, 10:52 p.m. |
| PD | Predicate disambiguation | batch_69d97dbdd94c8190ac4bbecca02dc77b |
completed | April 10, 2026, 10:46 p.m. |
| PDg | Predicate description generation | batch_69d97f1badac8190a59e60751f47b8d6 |
completed | April 10, 2026, 10:52 p.m. |
Created at: April 9, 2026, 8:40 p.m.