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.