Triple

T11959458
Position Surface form Disambiguated ID Type / Status
Subject CMake E284629 entity
Predicate maintainer P2962 FINISHED
Object Kitware E956222 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: Kitware | Statement: [CMake, maintainer, Kitware]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kitware
Context triple: [CMake, maintainer, Kitware]
  • A. Kitware chosen
    Kitware is a software research and development company best known for creating open-source tools and platforms for scientific computing, visualization, and software build management.
  • B. Inprise Corporation
    Inprise Corporation was the temporary name used by software company Borland during a late-1990s rebranding focused on enterprise solutions.
  • C. Eiffel Software
    Eiffel Software is a software company best known for developing the Eiffel programming language and tools that emphasize object-oriented design and software reliability.
  • D. The Qt Company
    The Qt Company is a Finnish software company best known for developing and maintaining the Qt cross-platform application and user interface framework used worldwide in desktop, mobile, and embedded systems.
  • E. Codership
    Codership is a software company best known for creating the Galera Cluster synchronous multi-master replication technology for MySQL and related databases.
  • 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_69d6ab2db38c8190b1f0ed6663ef8ada completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d9036941948190b150369094551731 completed April 10, 2026, 2:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69f471d625c88190baed4ea08853988a completed May 1, 2026, 9:26 a.m.
Created at: April 8, 2026, 9:45 p.m.