Triple
T32669254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AEVB |
E835244
|
entity |
| Predicate | arxivIdentifier |
P31984
|
FINISHED |
| Object | arXiv:1312.6114 |
—
|
LITERAL 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: arXiv:1312.6114 | Statement: [AEVB, arxivIdentifier, arXiv:1312.6114]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: arxivIdentifier Context triple: [AEVB, arxivIdentifier, arXiv:1312.6114]
-
A.
arxivId
chosen
Indicates that an entity (such as a paper or work) is associated with a specific arXiv identifier used to reference it in the arXiv repository.
-
B.
doi
Indicates that an entity has a specific Digital Object Identifier (DOI) assigned to it, representing a persistent, unique reference to that digital object.
-
C.
publishedAsArXivPreprint
Indicates that a work has been made publicly available in preprint form on the arXiv repository.
-
D.
isAcademicPublicationOf
Indicates that one entity is an academic publication (e.g., paper, article, or report) that has been produced by or is associated with another entity.
-
E.
hasDBLPAuthorId
Indicates that an entity is associated with a specific author identifier in the DBLP bibliographic database.
- F. None of above.
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_69f349303ccc8190a70d0f6e8a21d3fb |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6c7ab10a88190bc44bfb0e61ead52 |
completed | May 3, 2026, 3:57 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f617c08190a70ba880210f908c |
completed | May 3, 2026, 3:41 a.m. |
Created at: May 1, 2026, 1:08 a.m.