Triple
T21138029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HathiTrust Digital Library |
E520863
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | HathiTrust |
—
|
NE NERFINISHED |
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: HathiTrust | Statement: [HathiTrust Digital Library, shortName, HathiTrust]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: HathiTrust Context triple: [HathiTrust Digital Library, shortName, HathiTrust]
-
A.
HathiTrust Digital Library
chosen
HathiTrust Digital Library is a large-scale collaborative digital repository of scanned books and other materials from academic and research institutions worldwide.
-
B.
Library of Congress Online Catalog
The Library of Congress Online Catalog is the digital search system that provides public access to the Library of Congress’s vast collections of books, recordings, photographs, maps, and other materials.
-
C.
UN Digital Library
The UN Digital Library is an online platform providing comprehensive access to United Nations documents, publications, and archival materials.
-
D.
Biodiversity Heritage Library
The Biodiversity Heritage Library is a large open-access digital library that provides free online access to historical and contemporary literature on biodiversity and natural history from institutions around the world.
-
E.
Biblioteca Digital Hispánica
Biblioteca Digital Hispánica is the Spanish National Library’s main online portal providing free access to digitized books, manuscripts, maps, prints, and other cultural heritage materials from Spain’s historical collections.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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.