Triple
T699927
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USPS Retail Ground |
E13975
|
entity |
| Predicate | insurance |
P18388
|
FINISHED |
| Object | optional insurance available |
—
|
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: optional insurance available | Statement: [USPS Retail Ground, insurance, optional insurance available]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: insurance Context triple: [USPS Retail Ground, insurance, optional insurance available]
-
A.
insuranceType
Indicates the specific category or kind of insurance coverage associated with an entity or relationship.
-
B.
depositInsuranceCoverageInitial
Indicates the initial amount or scope of insurance protection provided for a deposit at the start of coverage.
-
C.
business
Indicates that an entity is engaged in commercial or professional activities, such as providing goods or services for profit.
-
D.
market
Indicates the act of promoting, advertising, or selling a product, service, or idea to potential buyers or target audiences.
-
E.
safety
Indicates that an entity provides, ensures, or is associated with protection from harm, danger, or risk for another entity or within a given context.
- F. None of above. chosen
Provenance (4 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_69a493406c408190957eeec9048a8fb6 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a544e3608190ac315c7aa9f88e7e |
completed | March 1, 2026, 8:44 p.m. |
| PD | Predicate disambiguation | batch_69a4a4ec8c748190b198492a0eea4445 |
completed | March 1, 2026, 8:43 p.m. |
| PDg | Predicate description generation | batch_69a4a54235548190b46218ea18f77341 |
completed | March 1, 2026, 8:44 p.m. |
Created at: March 1, 2026, 7:36 p.m.