Triple
T17006495
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jyutping |
E412583
|
entity |
| Predicate | comparedWith |
P278
|
FINISHED |
| Object | Cantonese Pinyin |
E130822
|
NE 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: Cantonese Pinyin | Statement: [Jyutping, comparedWith, Cantonese Pinyin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cantonese Pinyin Context triple: [Jyutping, comparedWith, Cantonese Pinyin]
-
A.
Hanyu Pinyin
Hanyu Pinyin is the official romanization system for Standard Mandarin Chinese, using the Latin alphabet to represent Chinese pronunciation.
-
B.
Jyutping
Jyutping is a Cantonese romanization system developed by the Linguistic Society of Hong Kong that uses Latin letters and numbers to represent Cantonese pronunciation.
-
C.
Tongyong Pinyin
Tongyong Pinyin is a romanization system for Mandarin Chinese that was once officially used in Taiwan as an alternative to Hanyu Pinyin.
-
D.
Guangdong Romanization
Guangdong Romanization is a Latin-based writing system developed to represent the sounds of Cantonese and other Yue Chinese dialects, primarily used in Guangdong province.
-
E.
Hong Kong Government Cantonese Romanization
chosen
Hong Kong Government Cantonese Romanization is an official system developed by the Hong Kong government for representing Cantonese sounds using the Latin alphabet, primarily for place names and administrative use.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d886cb581c8190ab05f4b429c9cd85 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d3831268819089286053a5acf653 |
completed | April 18, 2026, 6:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00dc2035848190bf299875d37c8ac7 |
completed | May 10, 2026, 7:27 p.m. |
Created at: April 10, 2026, 5:32 a.m.