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.