Triple

T21226545
Position Surface form Disambiguated ID Type / Status
Subject NSSF E523097 entity
Predicate uses P98 FINISHED
Object S-NSSAI NE NERFINISHED

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: S-NSSAI | Statement: [NSSF, uses, S-NSSAI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: S-NSSAI
Context triple: [NSSF, uses, S-NSSAI]
  • A. 5G Core
    5G Core is the cloud-native, service-based core network architecture that underpins 5G mobile systems, enabling advanced connectivity, slicing, and low-latency services.
  • B. Nudm
    Nudm is a 5G core network service-based interface used for communication between the Access and Mobility Management Function (AMF) and the Unified Data Management (UDM) for user and mobility-related data.
  • C. NG-RAN
    NG-RAN is the 5G New Radio access network architecture specified by 3GPP, encompassing gNodeBs and their interfaces to the 5G core.
  • D. 3GPP SA
    3GPP SA (Service and System Aspects) is the working group within the 3rd Generation Partnership Project responsible for overall system architecture, service requirements, and cross-domain coordination for mobile communication standards.
  • E. Network Slice Instance chosen
    A Network Slice Instance is a logically isolated, end-to-end 5G network partition tailored to specific service or customer requirements, providing dedicated resources and performance characteristics.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b512ad94819087942b2ed925185f completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e734ab3f6c819083e277ea1c33134e completed April 21, 2026, 8:26 a.m.
Created at: April 16, 2026, 3:44 p.m.