Triple

T13969861
Position Surface form Disambiguated ID Type / Status
Subject HITS algorithm E336027 entity
Predicate citationTitle P33185 FINISHED
Object Authoritative sources in a hyperlinked environment
"Authoritative sources in a hyperlinked environment" is the seminal research paper by Jon Kleinberg that introduced the HITS algorithm for identifying authoritative and hub pages on the web graph.
E1071096 NE FINISHED

How this triple was built (5 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: Authoritative sources in a hyperlinked environment | Statement: [HITS algorithm, citationTitle, Authoritative sources in a hyperlinked environment]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Authoritative sources in a hyperlinked environment
Context triple: [HITS algorithm, citationTitle, Authoritative sources in a hyperlinked environment]
  • A. Finding: Publishing and Linking on the Web
    "Finding: Publishing and Linking on the Web" is a W3C Technical Architecture Group document that provides best-practice guidance on how web resources should be published and linked to ensure durability, interoperability, and clarity on the Web.
  • B. The Anatomy of a Large-Scale Hypertextual Web Search Engine
    "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.
  • C. 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.
  • D. Proceedings of the Seventh International World Wide Web Conference
    Proceedings of the Seventh International World Wide Web Conference is a collected volume of peer-reviewed research papers from a major early web conference that helped shape the foundations of web technologies and search engines.
  • E. The Social Life of Information
    The Social Life of Information is an influential book by John Seely Brown and Paul Duguid that explores how social and organizational contexts shape the way information is created, shared, and used in the digital age.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Authoritative sources in a hyperlinked environment
Triple: [HITS algorithm, citationTitle, Authoritative sources in a hyperlinked environment]
Generated description
"Authoritative sources in a hyperlinked environment" is the seminal research paper by Jon Kleinberg that introduced the HITS algorithm for identifying authoritative and hub pages on the web graph.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Authoritative sources in a hyperlinked environment
Target entity description: "Authoritative sources in a hyperlinked environment" is the seminal research paper by Jon Kleinberg that introduced the HITS algorithm for identifying authoritative and hub pages on the web graph.
  • A. Finding: Publishing and Linking on the Web
    "Finding: Publishing and Linking on the Web" is a W3C Technical Architecture Group document that provides best-practice guidance on how web resources should be published and linked to ensure durability, interoperability, and clarity on the Web.
  • B. The Anatomy of a Large-Scale Hypertextual Web Search Engine
    "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.
  • C. 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.
  • D. Proceedings of the Seventh International World Wide Web Conference
    Proceedings of the Seventh International World Wide Web Conference is a collected volume of peer-reviewed research papers from a major early web conference that helped shape the foundations of web technologies and search engines.
  • E. The Social Life of Information
    The Social Life of Information is an influential book by John Seely Brown and Paul Duguid that explores how social and organizational contexts shape the way information is created, shared, and used in the digital age.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: citationTitle
Context triple: [HITS algorithm, citationTitle, Authoritative sources in a hyperlinked environment]
  • A. publicationTitle chosen
    Indicates the name or title under which a work (such as an article, book, or paper) is formally published.
  • B. title
    Indicates that one entity serves as the formal name or designation of another entity.
  • C. citationKey
    Indicates a unique identifier assigned to a specific citation or bibliographic reference within a collection of references.
  • D. citationType
    Indicates the specific kind or category of citation relationship that one entity has to another (e.g., reference, quotation, acknowledgment).
  • E. titleInSources
    Indicates that a specific title for an entity is attested or recorded in one or more external sources.
  • F. None of above.

Provenance (6 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_69d81c61f3508190aaf2ca0dc0002c59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2e8daeac8190aadd4b3b60222482 completed April 14, 2026, 12:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69fba1dc838c8190bbcfefd69ea29965 completed May 6, 2026, 8:17 p.m.
NEDg Description generation batch_69fba2b8e32081909cd32ed0bd255072 completed May 6, 2026, 8:21 p.m.
NED2 Entity disambiguation (via description) batch_69fba322460c81909aa36b661f39efcd completed May 6, 2026, 8:22 p.m.
PD Predicate disambiguation batch_69dd465a21408190b912a42c50ffa0d9 completed April 13, 2026, 7:39 p.m.
Created at: April 9, 2026, 10:18 p.m.