Triple
T36865918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goods and Services Tax (Canada) |
E911081
|
entity |
| Predicate | zeroRatedExamples |
P37727
|
FINISHED |
| Object | basic groceries |
—
|
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: basic groceries | Statement: [Goods and Services Tax (Canada), zeroRatedExamples, basic groceries]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: zeroRatedExamples Context triple: [Goods and Services Tax (Canada), zeroRatedExamples, basic groceries]
-
A.
zeroRatedFor
Indicates that a service, product, or data usage is exempt from standard charges or does not count against a user’s billed quota.
-
B.
zeroRatedSuppliesInclude
chosen
Indicates that the set of supplies in question includes items that are taxed at a zero rate (zero-rated) under the applicable tax or VAT rules.
-
C.
noPreservedExamples
Indicates that there are currently no surviving or preserved instances of the referenced item, work, or phenomenon.
-
D.
nonExample
Indicates that something is explicitly identified as not being an example or instance of a given concept, category, or pattern.
-
E.
extraExample
Indicates that something is provided as an additional, illustrative instance beyond the main or required examples.
- 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_69f76e80f6f0819091cba8e19b269615 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd6834cc8190aa27153d6a99f3bb |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf7890008190a8bc355ff2d61c86 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.