Triple
T699933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USPS Retail Ground |
E13975
|
entity |
| Predicate | maxWeightUnit |
P12631
|
FINISHED |
| Object | pounds |
—
|
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: pounds | Statement: [USPS Retail Ground, maxWeightUnit, pounds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maxWeightUnit Context triple: [USPS Retail Ground, maxWeightUnit, pounds]
-
A.
maximumWeight
Indicates the greatest allowable or observed weight value associated with an entity or relationship.
-
B.
maximumTakeoffWeight
Indicates the greatest allowable weight an aircraft can have at the start of its takeoff roll under specified conditions.
-
C.
unitOfMeasure
chosen
Indicates that one entity specifies the standard unit in which the quantity or value of another entity is measured.
-
D.
typeOfUnit
Indicates that one entity specifies the kind or category of measurement unit that the other entity belongs to.
-
E.
weight
Indicates a relationship where a numerical value quantifies how heavy an entity is, often used to measure or compare mass or load.
- 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.