Triple

T10593010
Position Surface form Disambiguated ID Type / Status
Subject University Libraries (University of South Carolina) E250038 entity
Predicate hasPart P35 FINISHED
Object Digital Collections (University of South Carolina Libraries)
Digital Collections (University of South Carolina Libraries) is an online repository providing access to digitized materials from the university’s special collections, archives, and other library holdings.
E873886 NE FINISHED

How this triple was built (4 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 Collections (University of South Carolina Libraries) | Statement: [University Libraries (University of South Carolina), hasPart, Digital Collections (University of South Carolina Libraries)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Digital Collections (University of South Carolina Libraries)
Context triple: [University Libraries (University of South Carolina), hasPart, Digital Collections (University of South Carolina Libraries)]
  • A. 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.
  • B. AUC Woodruff Library digital collections
    AUC Woodruff Library digital collections is an online repository providing access to digitized archival materials, manuscripts, photographs, and other scholarly resources related to the Atlanta University Center and African American history and culture.
  • C. UN Digital Library
    The UN Digital Library is an online platform providing comprehensive access to United Nations documents, publications, and archival materials.
  • D. HathiTrust Digital Library
    HathiTrust Digital Library is a large-scale collaborative digital repository of scanned books and other materials from academic and research institutions worldwide.
  • E. Special Collections and Archives
    Special Collections and Archives is the department at Southwestern University that preserves and provides access to rare books, manuscripts, university records, and other unique historical materials.
  • 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: Digital Collections (University of South Carolina Libraries)
Triple: [University Libraries (University of South Carolina), hasPart, Digital Collections (University of South Carolina Libraries)]
Generated description
Digital Collections (University of South Carolina Libraries) is an online repository providing access to digitized materials from the university’s special collections, archives, and other library holdings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Digital Collections (University of South Carolina Libraries)
Target entity description: Digital Collections (University of South Carolina Libraries) is an online repository providing access to digitized materials from the university’s special collections, archives, and other library holdings.
  • A. 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.
  • B. AUC Woodruff Library digital collections
    AUC Woodruff Library digital collections is an online repository providing access to digitized archival materials, manuscripts, photographs, and other scholarly resources related to the Atlanta University Center and African American history and culture.
  • C. UN Digital Library
    The UN Digital Library is an online platform providing comprehensive access to United Nations documents, publications, and archival materials.
  • D. HathiTrust Digital Library
    HathiTrust Digital Library is a large-scale collaborative digital repository of scanned books and other materials from academic and research institutions worldwide.
  • E. Special Collections and Archives
    Special Collections and Archives is the department at Southwestern University that preserves and provides access to rare books, manuscripts, university records, and other unique historical materials.
  • F. None of above. chosen

Provenance (5 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_69d381c9d3d48190a29ee491e1696a0e completed April 6, 2026, 9:50 a.m.
NER Named-entity recognition batch_69d5277da8048190add007ca0c37253e completed April 7, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69d95e85c49c8190a580536be07c0405 completed April 10, 2026, 8:33 p.m.
NEDg Description generation batch_69d95f80d0c48190b88e3a4b3e42279c completed April 10, 2026, 8:37 p.m.
NED2 Entity disambiguation (via description) batch_69d9602748608190b0c971accf44b7aa completed April 10, 2026, 8:40 p.m.
Created at: April 6, 2026, 12:40 p.m.