Triple

T18574781
Position Surface form Disambiguated ID Type / Status
Subject Substack E453956 entity
Predicate hasCompetitor P1375 FINISHED
Object Patreon 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: Patreon | Statement: [Substack, hasCompetitor, Patreon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Patreon
Context triple: [Substack, hasCompetitor, Patreon]
  • A. Patreon chosen
    Patreon is a membership-based crowdfunding platform that enables creators to earn recurring income directly from their fans.
  • B. PledgeMusic
    PledgeMusic was a now-defunct direct-to-fan crowdfunding platform that allowed musicians to raise money and engage supporters around album releases and other creative projects.
  • C. Indiegogo
    Indiegogo is a global crowdfunding platform that enables individuals and businesses to raise money for creative, entrepreneurial, and charitable projects through online campaigns.
  • D. Kickstarter
    Kickstarter is a popular online crowdfunding platform that enables creators to raise funds from backers for creative projects across fields like art, technology, film, and design.
  • E. Bandcamp
    Bandcamp is an online music platform that enables artists and labels to sell digital and physical releases directly to fans while offering streaming, discovery, and community features.
  • 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_69d8d38974308190a9174430ef256b73 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e543c8c0608190afc99235006bf87f completed April 19, 2026, 9:06 p.m.
Created at: April 10, 2026, 11:43 a.m.