Triple
T1104374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cantonese |
E25452
|
entity |
| Predicate | usedInCourts |
P23171
|
FINISHED |
| Object | language of court proceedings in Hong Kong |
—
|
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: language of court proceedings in Hong Kong | Statement: [Cantonese, usedInCourts, language of court proceedings in Hong Kong]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedInCourts Context triple: [Cantonese, usedInCourts, language of court proceedings in Hong Kong]
-
A.
usedCourt
Indicates that an entity made use of or participated in legal proceedings within a particular court.
-
B.
usedInLegalCitation
Indicates that one entity is referenced or relied upon as an authoritative source within a legal citation to support legal arguments or decisions.
-
C.
hasCourts
Indicates that an entity possesses, contains, or is equipped with one or more courts (e.g., legal, sports, or judicial facilities).
-
D.
usedInCase
Indicates that something (such as an item, method, or piece of information) is employed or applied within a particular case or instance.
-
E.
appearsInLaw
Indicates that a legal concept, entity, or reference is mentioned or included within a specific law or legal document.
- 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_69a49428d4448190b3b36991ceae87ce |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b9e1047481909af1cf8df2a01fff |
completed | March 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69a4b7472c848190b0643872f67084a2 |
completed | March 1, 2026, 10:01 p.m. |
| PDg | Predicate description generation | batch_69a4b7da38888190a118ef20ce4ae9aa |
completed | March 1, 2026, 10:04 p.m. |
Created at: March 1, 2026, 7:43 p.m.