Triple

T359408
Position Surface form Disambiguated ID Type / Status
Subject eBay E7814 entity
Predicate acquired P2511 FINISHED
Object PayPal E3336 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: PayPal | Statement: [eBay, acquired, PayPal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PayPal
Context triple: [eBay, acquired, PayPal]
  • A. PayPal chosen
    PayPal is a leading global online payment platform that enables individuals and businesses to send, receive, and manage digital payments securely over the internet.
  • B. Amazon Pay
    Amazon Pay is a digital payment service that lets customers use their Amazon accounts to make secure purchases and payments on third-party websites and apps.
  • C. PayPal Working Capital
    PayPal Working Capital is a business financing service that provides merchants with quick, fixed-fee loans repaid automatically as a percentage of their PayPal sales.
  • D. Pay.gov
    Pay.gov is a U.S. government online payment portal that allows individuals and businesses to securely make electronic payments to federal agencies.
  • E. Google Pay
    Google Pay is a digital wallet and online payment platform developed by Google that enables users to make secure contactless payments, in-app purchases, and online transactions using their devices.
  • 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_69a2e7e880008190a6ad7e06e5d03007 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ebb248608190b060553219616043 completed Feb. 28, 2026, 1:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3e578c1788190877cf6a346cf10d4 completed March 1, 2026, 7:06 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.