Triple

T16854474
Position Surface form Disambiguated ID Type / Status
Subject Amazon Ads E409750 entity
Predicate offersProduct P10882 FINISHED
Object Sponsored Products E409750 NE 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: Sponsored Products | Statement: [Amazon Ads, offersProduct, Sponsored Products]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sponsored Products
Context triple: [Amazon Ads, offersProduct, Sponsored Products]
  • A. Google Shopping
    Google Shopping is a Google service that lets users search for, compare, and discover products from various online retailers.
  • B. Amazon Ads chosen
    Amazon Ads is Amazon’s advertising platform that enables brands and sellers to reach shoppers across Amazon’s online properties and partner sites through a range of ad formats and targeting tools.
  • C. YouTube Shopping
    YouTube Shopping is a commerce feature on YouTube that lets creators showcase and sell products directly through their videos, live streams, and channel pages.
  • D. Platform Specialty Products
    Platform Specialty Products is a specialty chemicals and agricultural solutions company known for growing through acquisitions of niche chemical businesses.
  • E. Shopwise
    Shopwise is a Philippine supermarket and hypermarket chain known for offering a wide range of groceries and household goods at value-oriented prices.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d88395e6c88190b22730f335107c14 completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b37c6e808190975b14b228253029 completed April 18, 2026, 4:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00bb216fac81909d401c6b9911d1e0 completed May 10, 2026, 5:06 p.m.
Created at: April 10, 2026, 5:24 a.m.