Triple

T21279586
Position Surface form Disambiguated ID Type / Status
Subject UTRAN E524482 entity
Predicate radioInterface P23646 FINISHED
Object UTRA 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: UTRA | Statement: [UTRAN, radioInterface, UTRA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UTRA
Context triple: [UTRAN, radioInterface, UTRA]
  • A. UTRAN
    UTRAN (UMTS Terrestrial Radio Access Network) is the 3G radio access network architecture used in UMTS mobile communication systems to connect user devices to the core network.
  • B. UMTS chosen
    UMTS is a third-generation (3G) mobile telecommunications system that provides higher-speed voice and data services over cellular networks.
  • C. E-UTRAN
    E-UTRAN is the LTE mobile network’s air-interface subsystem that connects user devices to the core network via evolved base stations (eNodeBs).
  • D. HSUPA
    HSUPA (High-Speed Uplink Packet Access) is a 3G mobile telecommunication protocol that significantly increases uplink data speeds and network capacity for users.
  • E. LTE
    LTE (Long Term Evolution) is a high-speed wireless communication standard for mobile devices and data terminals, widely used as the foundation of 4G cellular networks.
  • 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_69e0b516293c819089458ea2ec85f85e completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e73659b56c8190af283348378b1cff completed April 21, 2026, 8:33 a.m.
Created at: April 16, 2026, 4:02 p.m.