Triple
T5622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Docuverse |
E110
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object |
universal digital library
The universal digital library is a conceptual global repository aiming to provide seamless, searchable access to all recorded human knowledge in digital form.
|
E1153
|
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: universal digital library | Statement: [Docuverse, hasAlternativeName, universal digital library]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: universal digital library Context triple: [Docuverse, hasAlternativeName, universal digital library]
-
A.
MIT Libraries
MIT Libraries is the academic library system of the Massachusetts Institute of Technology, supporting research, teaching, and learning across science, engineering, and related fields.
-
B.
Library of Congress
The Library of Congress is the national library of the United States and one of the world’s largest and most comprehensive research libraries, serving as the research arm of the U.S. Congress.
-
C.
Wholly New Forms of Encyclopedias
"Wholly New Forms of Encyclopedias" is a section of Vannevar Bush’s essay "As We May Think" that envisions future, highly interconnected and dynamically organized knowledge systems beyond traditional printed encyclopedias.
-
D.
Tozzer Library
Tozzer Library is Harvard University's primary research library for anthropology and archaeology, housing extensive collections on human cultures, languages, and material history.
-
E.
Penn Libraries
Penn Libraries is the integrated library system of the University of Pennsylvania, providing extensive research collections, digital resources, and academic support services to the university community.
- 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: universal digital library Triple: [Docuverse, hasAlternativeName, universal digital library]
Generated description
The universal digital library is a conceptual global repository aiming to provide seamless, searchable access to all recorded human knowledge in digital form.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: universal digital library Target entity description: The universal digital library is a conceptual global repository aiming to provide seamless, searchable access to all recorded human knowledge in digital form.
-
A.
MIT Libraries
MIT Libraries is the academic library system of the Massachusetts Institute of Technology, supporting research, teaching, and learning across science, engineering, and related fields.
-
B.
Library of Congress
The Library of Congress is the national library of the United States and one of the world’s largest and most comprehensive research libraries, serving as the research arm of the U.S. Congress.
-
C.
Wholly New Forms of Encyclopedias
"Wholly New Forms of Encyclopedias" is a section of Vannevar Bush’s essay "As We May Think" that envisions future, highly interconnected and dynamically organized knowledge systems beyond traditional printed encyclopedias.
-
D.
Tozzer Library
Tozzer Library is Harvard University's primary research library for anthropology and archaeology, housing extensive collections on human cultures, languages, and material history.
-
E.
Penn Libraries
Penn Libraries is the integrated library system of the University of Pennsylvania, providing extensive research collections, digital resources, and academic support services to the university community.
- 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_69a238d6b47881909e68288aed2fd858 |
completed | Feb. 28, 2026, 12:37 a.m. |
| NER | Named-entity recognition | batch_69a23ff0650c8190bea8724de0343e58 |
completed | Feb. 28, 2026, 1:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a243c6f10c81908305b9e03c79a6ae |
completed | Feb. 28, 2026, 1:24 a.m. |
| NEDg | Description generation | batch_69a2463b1a8881908e900ed76ae81a4d |
completed | Feb. 28, 2026, 1:34 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a246aa8d6481908a9cc6d66a0c0296 |
completed | Feb. 28, 2026, 1:36 a.m. |
Created at: Feb. 28, 2026, 12:40 a.m.