Triple
T5884296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hong Kong Government Cantonese Romanization |
E130822
|
entity |
| Predicate | usesFinalConsonants |
P67253
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Hong Kong Government Cantonese Romanization, usesFinalConsonants, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesFinalConsonants Context triple: [Hong Kong Government Cantonese Romanization, usesFinalConsonants, yes]
-
A.
hasConsonantHarmony
Indicates that the entities are related by a pattern where consonants within a linguistic unit adjust to share similar features, creating consonant harmony.
-
B.
hasConsonantSigns
Indicates that one entity possesses or includes consonant sign characters as part of its representation or structure.
-
C.
hasConsonantPhonemes
Indicates that an entity possesses or includes one or more consonant phonemes in its phonological system.
-
D.
hasConsonantGradation
Indicates that a word undergoes systematic alternation of its consonants (consonant gradation) in different morphological or phonological forms.
-
E.
hasClickConsonants
Indicates that the subject language includes click consonant sounds in its phonemic inventory.
- 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_69c0085628dc8190b334c1b44c067efc |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c03fe07b7081909f8577ec3a9a1a8d |
completed | March 22, 2026, 7:15 p.m. |
| PD | Predicate disambiguation | batch_69c0334bdc308190ad0d7199ab975588 |
completed | March 22, 2026, 6:22 p.m. |
| PDg | Predicate description generation | batch_69c03fdf954c8190ae97a5c9ce40bdfa |
completed | March 22, 2026, 7:15 p.m. |
Created at: March 22, 2026, 3:57 p.m.