Triple
T1315123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Right to Buy policy framework |
E28084
|
entity |
| Predicate | discountDependsOn |
P15880
|
FINISHED |
| Object | length of tenancy |
—
|
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: length of tenancy | Statement: [Right to Buy policy framework, discountDependsOn, length of tenancy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: discountDependsOn Context triple: [Right to Buy policy framework, discountDependsOn, length of tenancy]
-
A.
fareDiscount
Indicates that a reduced price is applied to a standard fare for a product or service.
-
B.
priceInfluencedBy
chosen
Indicates that the price of one entity is affected or determined by another specified factor or entity.
-
C.
offersDiscountsOn
Indicates that one entity provides price reductions or special discount deals specifically applied to another entity or its associated items or services.
-
D.
priceRelationship
Indicates a comparative relationship between the prices of two entities, such as one being higher, lower, or equal to the other.
-
E.
offersGrade
Indicates that one entity assigns or provides an academic grade or evaluation to another entity.
- 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_69a498532c3481909223b74af2e578df |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c1598f488190b01cf4c3f1e613a7 |
completed | March 1, 2026, 10:44 p.m. |
| PD | Predicate disambiguation | batch_69a4beebcb348190964bd7215811942c |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:55 p.m.