Triple

T6609919
Position Surface form Disambiguated ID Type / Status
Subject TUI fly Belgium E149210 entity
Predicate ICAOcode P419 FINISHED
Object JAF
JAF is the ICAO airline designator used by TUI fly Belgium, a Belgian leisure airline operating charter and scheduled flights mainly to holiday destinations.
 E602683 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: JAF | Statement: [TUI fly Belgium, ICAOcode, JAF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: JAF
Context triple: [TUI fly Belgium, ICAOcode, JAF]
  • A. JAF
    JAF is the acronym commonly used for the Jordanian Armed Forces, the military organization responsible for defending the Hashemite Kingdom of Jordan.
  • B. JAF
    JAF is the three-letter IATA airport code assigned to Jaffna International Airport in Sri Lanka.
  • C. Japanese Red Cross Society
    The Japanese Red Cross Society is Japan’s national humanitarian organization that provides disaster relief, medical services, and blood donation programs as part of the International Red Cross and Red Crescent Movement.
  • D. JFA
    JFA is the governing body responsible for overseeing and organizing football activities and competitions in Jordan.
  • E. JAC
    JAC is the commonly used abbreviation for the Judicial Appointments Commission, the body responsible for selecting candidates for judicial office in England and Wales.
  • 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: JAF
Triple: [TUI fly Belgium, ICAOcode, JAF]
Generated description
JAF is the ICAO airline designator used by TUI fly Belgium, a Belgian leisure airline operating charter and scheduled flights mainly to holiday destinations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: JAF
Target entity description: JAF is the ICAO airline designator used by TUI fly Belgium, a Belgian leisure airline operating charter and scheduled flights mainly to holiday destinations.
  • A. JAF
    JAF is the acronym commonly used for the Jordanian Armed Forces, the military organization responsible for defending the Hashemite Kingdom of Jordan.
  • B. JAF
    JAF is the three-letter IATA airport code assigned to Jaffna International Airport in Sri Lanka.
  • C. Japanese Red Cross Society
    The Japanese Red Cross Society is Japan’s national humanitarian organization that provides disaster relief, medical services, and blood donation programs as part of the International Red Cross and Red Crescent Movement.
  • D. JFA
    JFA is the governing body responsible for overseeing and organizing football activities and competitions in Jordan.
  • E. JAC
    JAC is the commonly used abbreviation for the Judicial Appointments Commission, the body responsible for selecting candidates for judicial office in England and Wales.
  • 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_69c687ebc680819094caf71faba2efe2 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6af3301dc819082d427675c36aaa6 completed March 27, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6cbd228fc8190852fac2308233765 completed March 27, 2026, 6:26 p.m.
NEDg Description generation batch_69c6cd417d288190868e9709deb4b28a completed March 27, 2026, 6:32 p.m.
NED2 Entity disambiguation (via description) batch_69c6ce6be1f88190bc8b90bf90c6dc55 completed March 27, 2026, 6:37 p.m.
Created at: March 27, 2026, 1:57 p.m.