Triple
T28706204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goods and Services Tax (Australia) |
E729702
|
entity |
| Predicate | zeroRatedFor |
P165241
|
FINISHED |
| Object | exports from Australia |
—
|
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: exports from Australia | Statement: [Goods and Services Tax (Australia), zeroRatedFor, exports from Australia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: zeroRatedFor Context triple: [Goods and Services Tax (Australia), zeroRatedFor, exports from Australia]
-
A.
ratedFor
Indicates that an entity has been evaluated and assigned a suitability or quality level for a particular purpose, context, or audience.
-
B.
ageRatingContext
Indicates the contextual basis or circumstances (such as region, system, or criteria) under which an age rating is assigned or interpreted.
-
C.
ageRatingControversy
Indicates that there is a dispute, concern, or notable issue regarding the appropriateness or assignment of an age rating for something.
-
D.
juvenileRating
Indicates that something has been evaluated and assigned a suitability or content rating specifically for juveniles or young audiences.
-
E.
hasContentRating
Indicates that something is associated with a specified content rating that reflects its suitability for particular audiences.
- 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_69f043e6e9688190b6bdd6e5665498ff |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f65705a3048190a3728b695ba2ae65 |
completed | May 2, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
| PDg | Predicate description generation | batch_69f6562ef4e4819082ce6abd41b74dc5 |
completed | May 2, 2026, 7:53 p.m. |
Created at: April 28, 2026, 5:45 a.m.