Triple
T16262609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norwegian domain name policy |
E394790
|
entity |
| Predicate | hasQuotaSystem |
P112673
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Norwegian domain name policy, hasQuotaSystem, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasQuotaSystem Context triple: [Norwegian domain name policy, hasQuotaSystem, yes]
-
A.
quotaSystem
chosen
Indicates a system in which fixed numerical limits or allocations are set for certain actions, resources, or participants.
-
B.
supportsProjectQuotas
Indicates that one entity provides or enables project-specific quota limits or enforcement for another entity.
-
C.
hasQuotationSystem
Indicates that an entity uses or is associated with a particular system or convention for representing quotations.
-
D.
oftenUsesQuotaType
Indicates that an entity frequently employs or relies on a particular type of quota in its typical operations or behavior.
-
E.
hasQuotient
Indicates that one quantity or entity is the result of dividing another quantity or entity by a specified divisor.
- 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_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e245c5583c8190901e892238cf8dbd |
completed | April 17, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69e219f259e88190bf49d8408c04178e |
completed | April 17, 2026, 11:30 a.m. |
Created at: April 10, 2026, 5:04 a.m.