Triple
T8614508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TIB – Leibniz Information Centre for Science and Technology and University Library |
E204000
|
entity |
| Predicate | operates |
P24
|
FINISHED |
| Object | TIB DOI registration service |
E663914
|
NE FINISHED |
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: TIB DOI registration service | Statement: [TIB – Leibniz Information Centre for Science and Technology and University Library, operates, TIB DOI registration service]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TIB DOI registration service Context triple: [TIB – Leibniz Information Centre for Science and Technology and University Library, operates, TIB DOI registration service]
-
A.
DOI
A DOI (Digital Object Identifier) is a persistent, unique alphanumeric string used to identify and provide a stable link to digital content such as scholarly articles, datasets, and other research outputs.
-
B.
DOI
DOI is the commonly used abbreviation for the United States Department of the Interior, the federal executive department responsible for managing the nation’s natural resources and public lands.
-
C.
DataCite
chosen
DataCite is a global non-profit organization that provides persistent identifiers (DOIs) and related services to help the research community reliably identify, share, and cite research data and other research outputs.
-
D.
ePIC Persistent Identifier Consortium
The ePIC Persistent Identifier Consortium is an international collaboration that provides and promotes persistent identifier services to support long-term access to digital research data and resources.
-
E.
Crossref
Crossref is a nonprofit organization that provides persistent digital identifiers and metadata services for scholarly content to support reliable citation linking and research discovery.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca832ceab8819096e4a9f546695079 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cc47020748819090f658c115c1a7b9 |
completed | March 31, 2026, 10:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cea91c30ec81908dafc1caf057e41c |
completed | April 2, 2026, 5:36 p.m. |
Created at: March 30, 2026, 6:25 p.m.