Triple
T699940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USPS Retail Ground |
E13975
|
entity |
| Predicate | dropOffOptions |
P18392
|
FINISHED |
| Object | Post Office retail counter |
—
|
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: Post Office retail counter | Statement: [USPS Retail Ground, dropOffOptions, Post Office retail counter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dropOffOptions Context triple: [USPS Retail Ground, dropOffOptions, Post Office retail counter]
-
A.
deliveryType
Indicates the method or mode by which a product, service, or item is delivered or fulfilled.
-
B.
takesAway
Indicates that one entity removes, deprives, or causes another entity to lose something it previously had.
-
C.
deliveryMode
Indicates the method or channel through which something (such as a product, service, or information) is delivered or provided.
-
D.
disbursementOption
Indicates the method or arrangement by which funds are paid out or distributed.
-
E.
deliveryGuarantee
Indicates that one party commits to ensuring that an item, service, or outcome will be delivered under specified conditions or within a defined timeframe.
- 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.