Triple
T699994
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Media Mail |
E13976
|
entity |
| Predicate | insuranceAvailability |
P7415
|
FINISHED |
| Object | optional insurance |
—
|
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 | Statement: [Media Mail, insuranceAvailability, optional insurance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: insuranceAvailability Context triple: [Media Mail, insuranceAvailability, optional insurance]
-
A.
insuranceType
Indicates the specific category or kind of insurance coverage associated with an entity or relationship.
-
B.
hasCoverage
Indicates that one entity provides insurance or protection coverage for another entity or subject.
-
C.
availability
chosen
Indicates that an entity is present, accessible, or ready for use or interaction by another entity.
-
D.
availableWith
Indicates that one entity can be obtained, accessed, or used in conjunction with another entity.
-
E.
availableAs
Indicates that one entity can be used, accessed, or offered in the form, role, or capacity of 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_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. |
Created at: March 1, 2026, 7:36 p.m.