Triple
T18567340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tailo |
E453788
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Pe̍h-ōe-jī |
—
|
NE NERFINISHED |
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: Pe̍h-ōe-jī | Statement: [Tailo, basedOn, Pe̍h-ōe-jī]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pe̍h-ōe-jī Context triple: [Tailo, basedOn, Pe̍h-ōe-jī]
-
A.
Pe̍h-ōe-jī
chosen
Pe̍h-ōe-jī is a Latin-based orthography developed by Western missionaries for writing Southern Min (Hokkien) and related Chinese dialects.
-
B.
Zhuyin
Zhuyin is a phonetic writing system for transcribing the sounds of Mandarin Chinese, primarily used in Taiwan for teaching pronunciation and literacy.
-
C.
Taiwanese Romanization System
The Taiwanese Romanization System is a standardized Latin-based orthography used to phonetically represent Taiwanese Hokkien.
-
D.
Hakka Romanization System
The Hakka Romanization System is a standardized method of writing the Hakka Chinese language using the Latin alphabet to represent its sounds and tones.
-
E.
McCune–Reischauer
McCune–Reischauer is a widely used system for romanizing the Korean language, designed to represent Korean pronunciation accurately using the Latin alphabet.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8d38974308190a9174430ef256b73 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53aff027481909ca7257967967650 |
completed | April 19, 2026, 8:28 p.m. |
Created at: April 10, 2026, 11:43 a.m.