Triple
T30662565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coach Outlet |
E780569
|
entity |
| Predicate | acceptsReturnsPolicy |
P9551
|
FINISHED |
| Object | outlet-specific return policy |
—
|
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: outlet-specific return policy | Statement: [Coach Outlet, acceptsReturnsPolicy, outlet-specific return policy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: acceptsReturnsPolicy Context triple: [Coach Outlet, acceptsReturnsPolicy, outlet-specific return policy]
-
A.
refundPolicy
chosen
Indicates the terms and conditions under which payments are returned or compensated after a purchase or transaction.
-
B.
conditionOfReturn
Indicates the specific terms or requirements under which something that was previously given, lent, or transferred must be returned.
-
C.
paymentPolicy
Indicates the rules, terms, and conditions governing how payments are expected to be made between the related parties.
-
D.
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.
-
E.
returnsAs
Indicates that one entity goes back to or resumes a previous state, location, role, or condition associated with 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_69f224a6d10481909290be1a00fc83b3 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68ae1d64481908f63a8c1393cd4dd |
completed | May 2, 2026, 11:38 p.m. |
| PD | Predicate disambiguation | batch_69f6861170d08190bb98be609d436f84 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:31 p.m.