Triple

T15709116
Position Surface form Disambiguated ID Type / Status
Subject Airlink E380788 entity
Predicate callsign P1565 FINISHED
Object LINK
LINK is the radio callsign used by the Irish regional airline Airlink for air traffic control communications.
E1172661 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: LINK | Statement: [Airlink, callsign, LINK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: LINK
Context triple: [Airlink, callsign, LINK]
  • A. Linky
    Linky is a French smart electricity meter system deployed nationwide to enable remote readings, real-time consumption monitoring, and improved grid management.
  • B. The Link
    The Link is a key University College Birmingham facility that provides modern teaching, learning, and student support spaces.
  • C. i.LINK
    i.LINK is Sony’s brand name for the IEEE 1394 high-speed serial bus interface used for connecting digital audio, video, and data devices.
  • D. U Link
    U Link is a successor student-focused service platform that continues and modernizes the functions previously provided under the name University Link.
  • E. LinkPass
    LinkPass is a type of transit fare product used within the same system as the CharlieTicket, providing riders with a pass-based option for public transportation access.
  • 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: LINK
Triple: [Airlink, callsign, LINK]
Generated description
LINK is the radio callsign used by the Irish regional airline Airlink for air traffic control communications.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: LINK
Target entity description: LINK is the radio callsign used by the Irish regional airline Airlink for air traffic control communications.
  • A. Linky
    Linky is a French smart electricity meter system deployed nationwide to enable remote readings, real-time consumption monitoring, and improved grid management.
  • B. The Link
    The Link is a key University College Birmingham facility that provides modern teaching, learning, and student support spaces.
  • C. i.LINK
    i.LINK is Sony’s brand name for the IEEE 1394 high-speed serial bus interface used for connecting digital audio, video, and data devices.
  • D. U Link
    U Link is a successor student-focused service platform that continues and modernizes the functions previously provided under the name University Link.
  • E. LinkPass
    LinkPass is a type of transit fare product used within the same system as the CharlieTicket, providing riders with a pass-based option for public transportation access.
  • 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_69d86d9bf930819082b30cf6d169297c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f8d8b648190842c635f2ae7bfa4 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff757b7e0c81909b32aecc093c93e4 completed May 9, 2026, 5:57 p.m.
NEDg Description generation batch_69ff76deb1948190bc49825719ac97d5 completed May 9, 2026, 6:03 p.m.
NED2 Entity disambiguation (via description) batch_69ff77642ba4819095c1acc65da06135 completed May 9, 2026, 6:05 p.m.
Created at: April 10, 2026, 4:45 a.m.