Triple
T699944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USPS Retail Ground |
E13975
|
entity |
| Predicate | oversizePolicy |
P18394
|
FINISHED |
| Object | oversized pricing may apply |
—
|
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: oversized pricing may apply | Statement: [USPS Retail Ground, oversizePolicy, oversized pricing may apply]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oversizePolicy Context triple: [USPS Retail Ground, oversizePolicy, oversized pricing may apply]
-
A.
farePolicySupport
Indicates that there is a policy in place governing fares (such as prices, discounts, or rules) that is recognized, enabled, or supported in the given context.
-
B.
reservationPolicy
Indicates the rules or conditions governing how reservations are made, modified, or canceled between parties.
-
C.
includesSizeRange
Indicates that one entity specifies or covers a particular range of sizes associated with another entity.
-
D.
overrides
Indicates that one entity replaces, supersedes, or takes precedence over another in determining the outcome or applicable behavior.
-
E.
sizeIncreasedTo
Indicates that an entity’s size has changed and reached a specified larger value or magnitude.
- 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.