Triple

T23136014
Position Surface form Disambiguated ID Type / Status
Subject Steve Case E577323 entity
Predicate coFounded P104 FINISHED
Object AOL NE NERFINISHED

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: AOL | Statement: [Steve Case, coFounded, AOL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AOL
Context triple: [Steve Case, coFounded, AOL]
  • A. AOL chosen
    AOL is a pioneering American internet and online services company best known for popularizing dial-up access and email in the 1990s and early 2000s.
  • B. AOL Desktop
    AOL Desktop is an all-in-one software suite that combines web browsing, email, instant messaging, and media services in a single interface, originally designed for users of the AOL online service.
  • C. Lycos
    Lycos is an early web search engine and internet portal that was popular in the 1990s alongside rivals like AltaVista and Yahoo.
  • D. Yahoo
    Yahoo is a pioneering web services company best known for its web portal, search engine, email service, and online media offerings.
  • E. Cox Internet
    Cox Internet is a major U.S. broadband and telecommunications service provider offering high-speed internet and related digital services to residential and business customers.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245f8e6248190ba3d58e068b4dccb completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18e8b694c8190b9ead00ea0576d90 completed April 29, 2026, 4:52 a.m.
Created at: April 17, 2026, 4 p.m.