Triple

T10082920
Position Surface form Disambiguated ID Type / Status
Subject Marthe Keller E213946 entity
Predicate notableWork P4 FINISHED
Object Fedora E101036 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: Fedora | Statement: [Marthe Keller, notableWork, Fedora]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fedora
Context triple: [Marthe Keller, notableWork, Fedora]
  • A. Fedora chosen
    Fedora is a 1978 drama film by Billy Wilder that explores the tragic mystique and hidden costs of Hollywood stardom.
  • B. Fedora Linux
    Fedora Linux is a community-driven, cutting-edge Linux distribution sponsored by Red Hat, known for integrating the latest open-source technologies and serving as a foundation for other projects and operating systems.
  • C. Rocky Linux
    Rocky Linux is a community-driven, enterprise-grade Linux distribution designed to be a bug-for-bug compatible downstream rebuild of Red Hat Enterprise Linux.
  • D. Fedora Silverblue
    Fedora Silverblue is an immutable, desktop-focused variant of Fedora Linux that delivers a stable, container-friendly operating system image designed for reliability and easy rollbacks.
  • E. Red Hat Enterprise Linux
    Red Hat Enterprise Linux is a commercially supported, enterprise-grade Linux distribution widely used for servers, cloud deployments, and mission-critical applications.
  • 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_69ca839bf730819086900c323c9b8c95 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd04352d081908f676444cd2d2578 completed April 2, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2b66b256c8190861066f7c19008d2 completed April 5, 2026, 7:22 p.m.
Created at: March 30, 2026, 9 p.m.