Triple

T20978055
Position Surface form Disambiguated ID Type / Status
Subject MIH Command Service E516677 entity
Predicate worksWith P398 FINISHED
Object MIH Information Service 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: MIH Information Service | Statement: [MIH Command Service, worksWith, MIH Information Service]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MIH Information Service
Context triple: [MIH Command Service, worksWith, MIH Information Service]
  • A. MIH Information Service chosen
    MIH Information Service is a component of the IEEE 802.21 framework that supplies network-related information to facilitate seamless handovers across heterogeneous wireless and wired networks.
  • B. MIH Services
    MIH Services refers to the IEEE 802.21 framework that enables seamless handover and interoperability between heterogeneous wireless and wired networks.
  • C. MIH
    MIH is the National Rail station code for Mills Hill railway station in Greater Manchester, England.
  • D. MIH
    MIH is a networking standard framework that enables seamless handover and mobility support across heterogeneous wireless and wired access technologies.
  • E. MIH
    MIH is the International Watchmaking Museum in La Chaux-de-Fonds, Switzerland, renowned for its extensive collections and exhibitions on the history and art of timekeeping.
  • 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_69e0b4fee5ac8190875fa9ceba1a5e5e completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fba65b0881908bc00981053edb68 completed April 21, 2026, 4:23 a.m.
Created at: April 16, 2026, 1:47 p.m.