Triple

T10023684
Position Surface form Disambiguated ID Type / Status
Subject Auto-Encoding Variational Bayes E200670 entity
Predicate archive P3262 FINISHED
Object arXiv E95183 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: arXiv | Statement: [Auto-Encoding Variational Bayes, archive, arXiv]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: arXiv
Context triple: [Auto-Encoding Variational Bayes, archive, arXiv]
  • A. arXiv chosen
    arXiv is an open-access repository of electronic preprints in fields such as physics, mathematics, computer science, and related disciplines, widely used by researchers to share and access scientific papers before formal peer-reviewed publication.
  • B. INSPIRE-HEP
    INSPIRE-HEP is a leading digital library and information system for high-energy physics literature, providing comprehensive indexing, citation data, and research tools for the global particle physics community.
  • C. Semantic Scholar
    Semantic Scholar is an AI-powered academic search engine that helps researchers discover and understand scientific literature more efficiently.
  • D. CiteSeerX
    CiteSeerX is a public digital library and search engine that focuses on indexing and providing access to scientific and academic research papers, particularly in computer and information science.
  • E. AAS Open Research
    AAS Open Research is an open-access publishing platform of the American Astronomical Society that supports rapid, transparent dissemination and peer review of research in astronomy and astrophysics.
  • 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_69ca831c45f08190ac1505cc15076608 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cdcd7c75548190aa604d90d63dc111 completed April 2, 2026, 1:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69d26abb0ab08190b5bcf101c5680f3c completed April 5, 2026, 1:59 p.m.
Created at: March 30, 2026, 8:53 p.m.