Triple

T21138047
Position Surface form Disambiguated ID Type / Status
Subject HathiTrust Digital Library E520863 entity
Predicate memberOf P10 FINISHED
Object Digital Preservation Network NE NERFINISHED

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: Digital Preservation Network | Statement: [HathiTrust Digital Library, memberOf, Digital Preservation Network]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Digital Preservation Network
Context triple: [HathiTrust Digital Library, memberOf, Digital Preservation Network]
  • A. International Internet Preservation Consortium
    The International Internet Preservation Consortium is a global alliance of libraries and cultural heritage institutions dedicated to preserving and providing long-term access to web content.
  • B. Stanford Digital Library Project
    The Stanford Digital Library Project was a pioneering research initiative at Stanford University in the 1990s that explored advanced technologies for organizing, searching, and accessing large-scale digital information, and it played a key role in the origins of Google.
  • C. CONTENTdm
    CONTENTdm is a digital collection management software platform widely used by libraries, archives, and museums to store, manage, and provide online access to digitized materials.
  • D. Duke Digital Collections platform
    The Duke Digital Collections platform is an online repository providing access to digitized materials from Duke University Libraries’ special and archival collections.
  • E. Digital Object Architecture
    Digital Object Architecture is a framework for uniquely identifying, managing, and interoperating digital information objects across distributed networks.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Digital Preservation Network
Target entity description: The Digital Preservation Network is a collaborative consortium of academic and research institutions dedicated to ensuring the long-term preservation and accessibility of digital scholarly content.
  • A. International Internet Preservation Consortium
    The International Internet Preservation Consortium is a global alliance of libraries and cultural heritage institutions dedicated to preserving and providing long-term access to web content.
  • B. Stanford Digital Library Project
    The Stanford Digital Library Project was a pioneering research initiative at Stanford University in the 1990s that explored advanced technologies for organizing, searching, and accessing large-scale digital information, and it played a key role in the origins of Google.
  • C. CONTENTdm
    CONTENTdm is a digital collection management software platform widely used by libraries, archives, and museums to store, manage, and provide online access to digitized materials.
  • D. Duke Digital Collections platform
    The Duke Digital Collections platform is an online repository providing access to digitized materials from Duke University Libraries’ special and archival collections.
  • E. Digital Object Architecture
    Digital Object Architecture is a framework for uniquely identifying, managing, and interoperating digital information objects across distributed networks.
  • F. None of above. chosen

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_69e0b50b53048190ae34e8abbe3c5ada completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7235d1c788190a28577a753532b2a completed April 21, 2026, 7:12 a.m.
Created at: April 16, 2026, 2:57 p.m.