Triple

T12844149
Position Surface form Disambiguated ID Type / Status
Subject Angela Beesley E307127 entity
Predicate hasBiographyOn P6570 FINISHED
Object Wikipedia E19879 NE FINISHED

How this triple was built (3 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: Wikipedia | Statement: [Angela Beesley, hasBiographyOn, Wikipedia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wikipedia
Context triple: [Angela Beesley, hasBiographyOn, Wikipedia]
  • A. Wikipedia chosen
    Wikipedia is a free, collaboratively edited online encyclopedia that allows users worldwide to create and modify its articles.
  • B. Abstract Wikipedia
    Abstract Wikipedia is a Wikimedia project aiming to create language-independent, structured representations of encyclopedia articles that can be rendered into many natural languages.
  • C. WikiWikiWeb
    WikiWikiWeb is the first-ever wiki website, launched in 1995 as a collaborative platform for software developers to share ideas and documentation.
  • D. britannica.com
    britannica.com is the official website of Encyclopaedia Britannica, offering a comprehensive, curated digital encyclopedia and educational resources.
  • E. Citizendium
    Citizendium is an expert-guided, wiki-based online encyclopedia project founded as an alternative to Wikipedia, emphasizing real-name authorship and expert oversight.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasBiographyOn
Context triple: [Angela Beesley, hasBiographyOn, Wikipedia]
  • A. hasBiographicalWork
    Indicates that there exists a biographical work (such as a book, article, or film) whose subject is the given entity.
  • B. isBiographerOf
    Indicates that one person has written a biography about another person.
  • C. biographyWrittenBy
    Indicates that a biography about a person or entity was authored by a specific writer.
  • D. hasBiographicalTheme
    Indicates that something (such as a work, text, or content) centers on or significantly involves biographical subject matter, such as a person’s life, experiences, or personal history.
  • E. includesBiographiesOf chosen
    Indicates that one entity contains or features biographical information about another entity.
  • F. None of above.

Provenance (4 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_69d7bdf52b94819096d6f0ba4ab50a98 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9714208f881908f7f8a921362909a completed April 10, 2026, 9:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a54838888190804202e45a55de48 completed May 3, 2026, 1:30 a.m.
PD Predicate disambiguation batch_69d96fa3002881908000357b1f95a3ac completed April 10, 2026, 9:46 p.m.
Created at: April 9, 2026, 5:36 p.m.