Triple

T14471997
Position Surface form Disambiguated ID Type / Status
Subject Dijon-Bourgogne Airport E358867 entity
Predicate IATAcode P418 FINISHED
Object DIJ
DIJ is the IATA airport code for Dijon-Bourgogne Airport, serving the city of Dijon in eastern France.
 E1100241 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: DIJ | Statement: [Dijon-Bourgogne Airport, IATAcode, DIJ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DIJ
Context triple: [Dijon-Bourgogne Airport, IATAcode, DIJ]
  • A. DI
    DI is the abbreviation for Defence Intelligence, the United Kingdom’s military intelligence organization responsible for providing strategic and operational intelligence to the government and armed forces.
  • B. dih
    dih is the ISO 639-3 code for Diegueño, a Yuman language traditionally spoken by the Kumeyaay people of southern California and northern Baja California.
  • C. DIAP
    DIAP is the ICAO airport code for Félix Houphouët-Boigny International Airport, the main international gateway serving Abidjan in Côte d'Ivoire.
  • D. JdI
    JdI is the standard abbreviation for the "Jahrbuch des Deutschen Archäologischen Instituts," a leading scholarly yearbook in the field of classical archaeology published by the German Archaeological Institute.
  • E. Di
    Di is a common shortened form of the given name Diana, often used as an affectionate nickname.
  • 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: DIJ
Triple: [Dijon-Bourgogne Airport, IATAcode, DIJ]
Generated description
DIJ is the IATA airport code for Dijon-Bourgogne Airport, serving the city of Dijon in eastern France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DIJ
Target entity description: DIJ is the IATA airport code for Dijon-Bourgogne Airport, serving the city of Dijon in eastern France.
  • A. DI
    DI is the abbreviation for Defence Intelligence, the United Kingdom’s military intelligence organization responsible for providing strategic and operational intelligence to the government and armed forces.
  • B. dih
    dih is the ISO 639-3 code for Diegueño, a Yuman language traditionally spoken by the Kumeyaay people of southern California and northern Baja California.
  • C. DIAP
    DIAP is the ICAO airport code for Félix Houphouët-Boigny International Airport, the main international gateway serving Abidjan in Côte d'Ivoire.
  • D. JdI
    JdI is the standard abbreviation for the "Jahrbuch des Deutschen Archäologischen Instituts," a leading scholarly yearbook in the field of classical archaeology published by the German Archaeological Institute.
  • E. Di
    Di is a common shortened form of the given name Diana, often used as an affectionate nickname.
  • 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_69d827966698819082e140837737501d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de91fab21c819090b6e209d8efba6e completed April 14, 2026, 7:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd649e103c81908001b45c16d1fd79 completed May 8, 2026, 4:20 a.m.
NEDg Description generation batch_69fd658f2c1c8190b6a564dbe75fc2f2 completed May 8, 2026, 4:24 a.m.
NED2 Entity disambiguation (via description) batch_69fd661c201c8190ba8ce1295849e8c1 completed May 8, 2026, 4:27 a.m.
Created at: April 10, 2026, 1:20 a.m.