Triple
T699904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First-Class Mail |
E13974
|
entity |
| Predicate | handlingPriority |
P1616
|
FINISHED |
| Object | processed before USPS Marketing Mail |
—
|
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: processed before USPS Marketing Mail | Statement: [First-Class Mail, handlingPriority, processed before USPS Marketing Mail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: handlingPriority Context triple: [First-Class Mail, handlingPriority, processed before USPS Marketing Mail]
-
A.
handles
Indicates that one entity is responsible for dealing with, managing, or taking care of another entity or task.
-
B.
messageHandling
Indicates how messages are received, processed, and responded to within a communication or messaging system.
-
C.
treatyApprovalPriority
Indicates the relative importance or urgency assigned to approving a particular treaty compared to other treaties or legislative actions.
-
D.
holding
Indicates that one entity is physically grasping, carrying, or keeping another entity in its possession or control.
-
E.
confersPrecedenceIn
chosen
Indicates that one entity is granted higher priority, rank, or standing over another within a specified context or domain.
- 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.