Triple
T33647718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norse Rewards |
E862004
|
entity |
| Predicate | customerRelationshipType |
P99211
|
FINISHED |
| Object | retention program |
—
|
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: retention program | Statement: [Norse Rewards, customerRelationshipType, retention program]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: customerRelationshipType Context triple: [Norse Rewards, customerRelationshipType, retention program]
-
A.
relationshipToCustomers
chosen
Indicates the type or nature of connection an entity has with its customers, such as role, status, or interaction pattern.
-
B.
relationshipType
Indicates the specific kind of relationship that exists between two or more entities.
-
C.
customerType
Indicates the classification or category assigned to a customer based on their characteristics, status, or relationship with a business.
-
D.
relationshipTypeStart
Indicates the type or category of relationship that begins or is initiated at a specific point or event.
-
E.
referralRelationship
Indicates a relationship in which one entity directs or recommends another entity to a third party for services, information, or further action.
- 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_69f3498280c48190bcc3494017d14234 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6ffbad8848190867c2988c0ceb84f |
completed | May 3, 2026, 7:56 a.m. |
| PD | Predicate disambiguation | batch_69f6fc5740fc81909774a4f65201a3ff |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:42 a.m.