Triple

T16231407
Position Surface form Disambiguated ID Type / Status
Subject Balıkesir Air Base E393989 entity
Predicate hasIataCode P2569 FINISHED
Object BZI
BZI is the IATA airport code for Balıkesir Air Base, a military airfield located near Balıkesir in western Turkey.
 E1200613 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: BZI | Statement: [Balıkesir Air Base, hasIataCode, BZI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BZI
Context triple: [Balıkesir Air Base, hasIataCode, BZI]
  • A. BZ
    BZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Belize.
  • B. BZ
    BZ is the commonly used abbreviation for the Ministry of Foreign Affairs of the Netherlands, which is responsible for the country’s foreign policy and international relations.
  • C. BZ
    BZ is the vehicle registration code used on license plates for the municipality of Rammenau in Germany.
  • D. BZ
    BZ is the vehicle registration code used for the district and city of Bautzen in the German state of Saxony.
  • E. BZV
    BZV is the IATA airport code for Maya-Maya Airport, the main international airport serving Brazzaville in the Republic of the Congo.
  • 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: BZI
Triple: [Balıkesir Air Base, hasIataCode, BZI]
Generated description
BZI is the IATA airport code for Balıkesir Air Base, a military airfield located near Balıkesir in western Turkey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BZI
Target entity description: BZI is the IATA airport code for Balıkesir Air Base, a military airfield located near Balıkesir in western Turkey.
  • A. BZ
    BZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Belize.
  • B. BZ
    BZ is the commonly used abbreviation for the Ministry of Foreign Affairs of the Netherlands, which is responsible for the country’s foreign policy and international relations.
  • C. BZ
    BZ is the vehicle registration code used on license plates for the municipality of Rammenau in Germany.
  • D. BZ
    BZ is the vehicle registration code used for the district and city of Bautzen in the German state of Saxony.
  • E. BZV
    BZV is the IATA airport code for Maya-Maya Airport, the main international airport serving Brazzaville in the Republic of the Congo.
  • 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_69d87f204df88190a8f88923decf9835 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e23d29fa248190943f4c3f7808908b completed April 17, 2026, 2:01 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0007a0ab08819082aea4c312c9ffc7 completed May 10, 2026, 4:20 a.m.
NEDg Description generation batch_6a00098ea3e48190b0744f1eafab9ce2 completed May 10, 2026, 4:29 a.m.
NED2 Entity disambiguation (via description) batch_6a0009fb40a48190b82f6de80226d306 completed May 10, 2026, 4:30 a.m.
Created at: April 10, 2026, 5:04 a.m.