Triple
T27353813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | European community in Hong Kong |
E685628
|
entity |
| Predicate | typicalVisaStatus |
P200748
|
FINISHED |
| Object | employment visa holders |
—
|
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: employment visa holders | Statement: [European community in Hong Kong, typicalVisaStatus, employment visa holders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalVisaStatus Context triple: [European community in Hong Kong, typicalVisaStatus, employment visa holders]
-
A.
typicalCustomsStatus
Indicates the usual or standard customs-related condition or classification that typically applies to an entity or transaction.
-
B.
typicalBusinessStatus
Indicates the usual or standard operational status or condition of a business (e.g., active, inactive, seasonal) under normal circumstances.
-
C.
typicalTourStatus
Indicates the usual or expected status or condition that a tour is in under normal circumstances.
-
D.
typicalStudentStatus
Indicates the usual or standard enrollment or academic standing that a student typically holds within an educational context.
-
E.
typicalMigrationStatus
Indicates the usual or characteristic migration state or pattern associated with an entity.
- 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_69ef14887c288190931b8431fdbf53c4 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69ffab5adf2c819084700c5ea34615bf |
completed | May 9, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69ffaabffa208190b5214ca17cc8a5ea |
completed | May 9, 2026, 9:44 p.m. |
| PDg | Predicate description generation | batch_69ffab59fe408190b72f13016de9953c |
completed | May 9, 2026, 9:47 p.m. |
Created at: April 27, 2026, 11:50 a.m.