Triple

T7033859
Position Surface form Disambiguated ID Type / Status
Subject JRun E163331 entity
Predicate supportsTechnology P5090 FINISHED
Object RMI E68048 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: RMI | Statement: [JRun, supportsTechnology, RMI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RMI
Context triple: [JRun, supportsTechnology, RMI]
  • A. RMI
    RMI is an institute at the University of California, Davis dedicated to research, education, and outreach in wine, food science, and related disciplines.
  • B. RMI
    RMI is the commonly used abbreviation for the Republic of the Marshall Islands, a Pacific island nation composed of atolls and islands.
  • C. Java RMI chosen
    Java RMI is a Java-based distributed object technology that enables remote method invocation between JVMs, allowing objects in different processes or networked machines to communicate as if they were local.
  • D. RMF
    RMF (Resource Measurement Facility) is an IBM performance monitoring and reporting tool used to analyze and manage system resources on z/OS mainframe environments.
  • E. RIMS
    RIMS (Ranging and Integrity Monitoring Station) is a ground-based monitoring facility used in satellite navigation systems like EGNOS to track GNSS signals and support accuracy and integrity corrections.
  • 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_69c6885d691c81908cf7d31083113886 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e2118fc88190a0751ca18eafb4a5 completed March 27, 2026, 8:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7759c8e408190a7d457e77a44ee26 completed March 28, 2026, 6:30 a.m.
Created at: March 27, 2026, 2:36 p.m.