Triple
T31265745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hong Kong residents |
E797248
|
entity |
| Predicate | commonlySpeak |
P72909
|
FINISHED |
| Object | Cantonese |
—
|
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: Cantonese | Statement: [Hong Kong residents, commonlySpeak, Cantonese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commonlySpeak Context triple: [Hong Kong residents, commonlySpeak, Cantonese]
-
A.
typicalLanguageUse
chosen
Indicates that one entity is the language most commonly or habitually used by another entity in ordinary communication or contexts.
-
B.
spokeWords
Indicates that one entity verbally expressed specific words to another entity or audience.
-
C.
commonsSpeaker
Indicates that a person serves as the Speaker (presiding officer) of the House of Commons.
-
D.
speaksIn
Indicates that an entity uses or expresses itself in a particular language or medium when speaking.
-
E.
oftenSays
Indicates that one entity frequently makes a particular statement or remark, or regularly expresses a certain idea or phrase.
- F. None of above.
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_69f224de2bbc819081af6c32e1d857b9 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fdb45537288190b6791078d4a6899f |
completed | May 8, 2026, 10 a.m. |
| PD | Predicate disambiguation | batch_69fdb39ad96481908376d7def9fafc13 |
completed | May 8, 2026, 9:57 a.m. |
Created at: April 29, 2026, 9:12 p.m.