Triple
T10958999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ng |
E258916
|
entity |
| Predicate | languageOfRomanization |
P42524
|
FINISHED |
| Object | Cantonese |
E25452
|
NE FINISHED |
How this triple was built (3 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 | Statement: [Ng, languageOfRomanization, Cantonese]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cantonese Context triple: [Ng, languageOfRomanization, Cantonese]
-
A.
Cantonese
chosen
Cantonese is a major Chinese language variety spoken primarily in Guangdong province, Hong Kong, Macau, and among overseas Chinese communities worldwide.
-
B.
Hong Kong Hakka
Hong Kong Hakka is a regional variety of the Hakka Chinese language traditionally spoken by Hakka communities in Hong Kong, reflecting local phonological and lexical influences.
-
C.
Teochew
Teochew is a Southern Min Chinese dialect originating from the Chaoshan region of Guangdong, widely spoken in overseas Chinese communities across Southeast Asia.
-
D.
Taiwanese Hakka
Taiwanese Hakka is a variety of the Hakka Chinese language spoken primarily by Hakka communities in Taiwan, characterized by distinct phonological and lexical features compared to other Hakka dialects.
-
E.
Huizhou Chinese
Huizhou Chinese is a distinctive group of Sinitic dialects spoken in the Huizhou region of southern Anhui, noted for its phonological complexity and significant divergence from Mandarin and other major Chinese varieties.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfRomanization Context triple: [Ng, languageOfRomanization, Cantonese]
-
A.
hasRomanizationOf
Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
-
B.
hasRomanizationStandard
Indicates that an entity’s romanized form follows a specified romanization standard or system.
-
C.
hasHakkaRomanization
Indicates that an entity is associated with a specific representation of its name or term in Hakka Romanization.
-
D.
romanizationOccurred
Indicates that a process of converting text from one writing system into the Roman (Latin) alphabet has taken place.
-
E.
transliterationLanguage
chosen
Indicates the language whose writing system is used as the target when converting text from one script to another.
- F. None of above.
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_69d6aa88500c819097d7032ca578e74f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d77127b10481908ad1efafb2a338d1 |
completed | April 9, 2026, 9:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e2d751e8e081908f31ab2d82105c3c |
completed | April 18, 2026, 12:58 a.m. |
| PD | Predicate disambiguation | batch_69d72e874f48819096ffa878f90c7d5b |
completed | April 9, 2026, 4:43 a.m. |
Created at: April 8, 2026, 9:23 p.m.