Triple

T16807750
Position Surface form Disambiguated ID Type / Status
Subject Inmarsat E408521 entity
Predicate notableProduct P1448 FINISHED
Object BGAN
BGAN is a global mobile satellite communications service that provides broadband data and voice connectivity to users in remote and hard-to-reach locations.
E1234878 NE FINISHED

How this triple was built (4 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: BGAN | Statement: [Inmarsat, notableProduct, BGAN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BGAN
Context triple: [Inmarsat, notableProduct, BGAN]
  • A. BGN
    BGN is the standard abbreviation for the U.S. Board on Geographic Names, the federal body that maintains uniform geographic name usage across the United States government.
  • B. BGN
    BGN is the official currency code for the Bulgarian lev, the national currency of Bulgaria.
  • C. BGN
    BGN is the National Rail station code for Bridgend railway station in South Wales, United Kingdom.
  • D. BG
    BG is the two-letter ISO 3166-1 alpha-2 country code representing Bulgaria.
  • E. BG
    BG is the vehicle registration code used for Belgrade, the capital city of Serbia.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: BGAN
Triple: [Inmarsat, notableProduct, BGAN]
Generated description
BGAN is a global mobile satellite communications service that provides broadband data and voice connectivity to users in remote and hard-to-reach locations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: BGAN
Target entity description: BGAN is a global mobile satellite communications service that provides broadband data and voice connectivity to users in remote and hard-to-reach locations.
  • A. BGN
    BGN is the National Rail station code for Bridgend railway station in South Wales, United Kingdom.
  • B. BGN
    BGN is the official currency code for the Bulgarian lev, the national currency of Bulgaria.
  • C. BGN
    BGN is the standard abbreviation for the U.S. Board on Geographic Names, the federal body that maintains uniform geographic name usage across the United States government.
  • D. BG
    BG is the vehicle registration code used for Belgrade, the capital city of Serbia.
  • E. BG
    BG is the two-letter ISO 3166-1 alpha-2 country code representing Bulgaria.
  • F. None of above. chosen

Provenance (5 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_69d88393905081908d00a86b99996ac8 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b2cde590819080dc474292b023ee completed April 18, 2026, 4:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b28f125481909664363904f4c031 completed May 10, 2026, 4:30 p.m.
NEDg Description generation batch_6a00b399786c8190acbd188ab55b1fa0 completed May 10, 2026, 4:34 p.m.
NED2 Entity disambiguation (via description) batch_6a00b466ecd08190b7b5ee54476631ab completed May 10, 2026, 4:37 p.m.
Created at: April 10, 2026, 5:22 a.m.