Triple

T7939358
Position Surface form Disambiguated ID Type / Status
Subject CRI-O E184353 entity
Predicate supports P516 FINISHED
Object AppArmor E37339 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: AppArmor | Statement: [CRI-O, supports, AppArmor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AppArmor
Context triple: [CRI-O, supports, AppArmor]
  • A. AppArmor chosen
    AppArmor is a Linux kernel security module that confines programs to a limited set of resources using per-application security profiles to reduce the impact of vulnerabilities and attacks.
  • B. SELinux
    SELinux (Security-Enhanced Linux) is a Linux kernel security module that provides a flexible, fine-grained mandatory access control (MAC) framework to enforce strict security policies on systems.
  • C. Luks
    Luks is the surname of American realist painter and Ashcan School member George Luks.
  • D. XProtect
    XProtect is a video management software platform widely used for managing and recording IP-based surveillance systems.
  • E. Capsicum capability framework
    The Capsicum capability framework is a security model and API for fine-grained sandboxing and privilege separation in Unix-like operating systems.
  • 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_69ca8290c21c8190906a5ca6fe2b03c4 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3b0983388190a77e8d5d899c5130 completed March 31, 2026, 3:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5c0e868481908748d340244ea8ea completed March 31, 2026, 5:30 a.m.
Created at: March 30, 2026, 5:08 p.m.