Triple

T5997147
Position Surface form Disambiguated ID Type / Status
Subject Ben Huh E133498 entity
Predicate founded P104 FINISHED
Object Cheezburger Network E560778 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: Cheezburger Network | Statement: [Ben Huh, founded, Cheezburger Network]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cheezburger Network
Context triple: [Ben Huh, founded, Cheezburger Network]
  • A. Cheezburger Network chosen
    Cheezburger Network is a humor and entertainment website network best known for hosting viral meme and image macro sites like I Can Has Cheezburger?.
  • B. Gawker Media
    Gawker Media was a now-defunct American online media company known for its network of influential blogs covering gossip, technology, feminism, and pop culture.
  • C. I Can Has Cheezburger?
    I Can Has Cheezburger? is a pioneering humor website and meme hub best known for popularizing LOLcats—images of cats with humorous, intentionally misspelled captions.
  • D. The Onion
    The Onion is a distinctive, modernist London building known for its layered, bulb-like architectural design that resembles the shape of an onion.
  • E. Funny or Die
    Funny or Die is a comedy video website and production company known for its celebrity-driven sketches and viral online content.
  • 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_69c00870ddbc81909880fa3864f4f38d completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04ee274e08190b6478c7ae318ae48 completed March 22, 2026, 8:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69c11cdec5608190ad093a09acd32ebf completed March 23, 2026, 10:58 a.m.
Created at: March 22, 2026, 4:05 p.m.