Triple

T15834277
Position Surface form Disambiguated ID Type / Status
Subject Rocket Delivery E383945 entity
Predicate serviceBrand P34842 FINISHED
Object Coupang Rocket E79665 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: Coupang Rocket | Statement: [Rocket Delivery, serviceBrand, Coupang Rocket]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Coupang Rocket
Context triple: [Rocket Delivery, serviceBrand, Coupang Rocket]
  • A. Coupang chosen
    Coupang is a South Korean e-commerce company often called the “Amazon of Korea,” known for its ultra-fast delivery service and dominant online retail platform.
  • B. Coupang Eats
    Coupang Eats is a South Korean food delivery platform operated by e-commerce giant Coupang, offering on-demand meal ordering from local restaurants.
  • C. Gmarket
    Gmarket is a major South Korean online marketplace platform offering a wide range of products from various sellers.
  • D. Naver Pay
    Naver Pay is a South Korean digital payment and fintech service that enables users to make online and mobile transactions within Naver’s ecosystem and at affiliated merchants.
  • E. Instacart
    Instacart is a U.S.-based grocery delivery and pickup service that partners with local retailers to let customers order groceries online for same-day fulfillment.
  • 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_69d86da34c888190976e06c4019d415a completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e11e6670d48190a456581dd951f168 completed April 16, 2026, 5:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffeb7f3c9481908bdde67998263c5e completed May 10, 2026, 2:20 a.m.
Created at: April 10, 2026, 4:49 a.m.