Triple

T6175488
Position Surface form Disambiguated ID Type / Status
Subject Harvard Dataverse E137807 entity
Predicate shortName P43 FINISHED
Object Dataverse E188107 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: Dataverse | Statement: [Harvard Dataverse, shortName, Dataverse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dataverse
Context triple: [Harvard Dataverse, shortName, Dataverse]
  • A. Dataverse chosen
    Dataverse is Microsoft's cloud-based data platform that securely stores, manages, and structures business data for use across Power Platform applications and services.
  • B. Harvard Dataverse
    Harvard Dataverse is a research data repository platform that enables scholars to share, publish, and preserve datasets, primarily used by the academic community.
  • C. Open Data Index
    Open Data Index is a global initiative that evaluates and ranks the openness and accessibility of government data across countries.
  • D. Open Data Lab
    Open Data Lab is a World Wide Web Foundation initiative that supports the use of open data to drive social impact, innovation, and better governance, particularly in developing countries.
  • E. Dimensions (research database)
    Dimensions is a comprehensive research database and analytics platform that aggregates scholarly publications, citations, grants, patents, and clinical trials to support discovery and evaluation across the research lifecycle.
  • 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_69c008a80f748190ba3d07ffc81acb29 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05dc70ac481909fd1db0d69837eca completed March 22, 2026, 9:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c141b69c348190a4e530b7380b643f completed March 23, 2026, 1:35 p.m.
Created at: March 22, 2026, 4:18 p.m.