Triple

T3196704
Position Surface form Disambiguated ID Type / Status
Subject PageRank E66951 entity
Predicate describedInPaper P519 FINISHED
Object The Anatomy of a Large-Scale Hypertextual Web Search Engine E68398 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: The Anatomy of a Large-Scale Hypertextual Web Search Engine | Statement: [PageRank, describedInPaper, The Anatomy of a Large-Scale Hypertextual Web Search Engine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: The Anatomy of a Large-Scale Hypertextual Web Search Engine
Context triple: [PageRank, describedInPaper, The Anatomy of a Large-Scale Hypertextual Web Search Engine]
  • A. The Anatomy of a Large-Scale Hypertextual Web Search Engine chosen
    "The Anatomy of a Large-Scale Hypertextual Web Search Engine" is a seminal research paper by Sergey Brin and Larry Page that introduced the design and PageRank algorithm behind the early Google search engine.
  • B. PageRank algorithm
    The PageRank algorithm is a link analysis method used by search engines, notably Google, to rank web pages in search results based on their importance within the web’s link structure.
  • C. ACM International Conference on Web Search and Data Mining
    The ACM International Conference on Web Search and Data Mining (WSDM) is a leading annual computer science research conference focusing on web search, data mining, and related areas of information retrieval and machine learning.
  • D. Architecture of the World Wide Web, Volume One
    Architecture of the World Wide Web, Volume One is a W3C-authored technical document that defines the foundational principles and design of the Web’s architecture.
  • E. Finding: The Self-Describing Web
    "Finding: The Self-Describing Web" is a W3C Technical Architecture Group document that explains how web resources should carry or link to enough metadata and semantics to allow automated agents and humans to understand and use them without prior agreement.
  • 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_69ad8588ba18819086a10951c32ecb80 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada7177b488190b7a1b40ff3fae15f completed March 8, 2026, 4:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69b24bb2c9908190b3abc395537e22ac completed March 12, 2026, 5:14 a.m.
Created at: March 8, 2026, 3:07 p.m.