Triple

T14921986
Position Surface form Disambiguated ID Type / Status
Subject Safarilink Aviation E371535 entity
Predicate callsign P1565 FINISHED
Object SAFARILINK E371535 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: SAFARILINK | Statement: [Safarilink Aviation, callsign, SAFARILINK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SAFARILINK
Context triple: [Safarilink Aviation, callsign, SAFARILINK]
  • A. Safarilink Aviation chosen
    Safarilink Aviation is a Kenyan regional airline specializing in scheduled and charter flights to safari and tourist destinations across East Africa.
  • B. Suddenlink Communications
    Suddenlink Communications is a U.S.-based cable television and broadband internet provider that served residential and business customers, particularly in smaller and mid-sized markets.
  • C. Opal Telecom
    Opal Telecom was a UK-based telecommunications provider that became part of TalkTalk’s business services operations following its acquisition.
  • D. Southern Telecom
    Southern Telecom is a telecommunications subsidiary of Southern Company that provides fiber-optic network and related communication services.
  • E. Cox Communications
    Cox Communications is a major American telecommunications company that provides cable television, internet, and phone services to residential and business customers.
  • 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_69d85cc7ea3481908228b5acb7d06f12 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded63121e48190b54eb2546acc3c93 completed April 15, 2026, 12:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe72c141088190936f2fd53fee80e4 completed May 8, 2026, 11:33 p.m.
Created at: April 10, 2026, 2:34 a.m.