Triple
T8409171
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Canada Pension Plan |
E198577
|
entity |
| Predicate | indexation |
P14569
|
FINISHED |
| Object | benefits indexed to inflation |
—
|
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: benefits indexed to inflation | Statement: [Canada Pension Plan, indexation, benefits indexed to inflation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: indexation Context triple: [Canada Pension Plan, indexation, benefits indexed to inflation]
-
A.
benefitIndexation
chosen
Indicates that a benefit amount is adjusted over time according to an index (such as inflation or wage growth).
-
B.
isPriceIndex
Indicates that a value represents a price index, expressing the relative level or change of prices compared to a reference point or period.
-
C.
indexType
Indicates the classification or category of an index associated with an entity or structure.
-
D.
indexStructure
Indicates that one entity serves as an index or organizational framework that structures, arranges, or provides access to another entity or set of entities.
-
E.
indexingService
Indicates a service that organizes, catalogs, and maintains an index of items or data so they can be efficiently searched and retrieved.
- 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_69ca831201b481909e137936ef99ff11 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb8317045c8190b69cc99854b633be |
completed | March 31, 2026, 8:17 a.m. |
| PD | Predicate disambiguation | batch_69cb70d473dc8190af8ea81ee5aa970d |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6:05 p.m.