Triple

T6937426
Position Surface form Disambiguated ID Type / Status
Subject Zagreb Franjo Tuđman Airport E160587 entity
Predicate IATAcode P418 FINISHED
Object ZAG
ZAG is the three-letter IATA airport code for Zagreb Franjo Tuđman Airport, the main international airport serving Croatia’s capital city, Zagreb.
 E629384 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: ZAG | Statement: [Zagreb Franjo Tuđman Airport, IATAcode, ZAG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ZAG
Context triple: [Zagreb Franjo Tuđman Airport, IATAcode, ZAG]
  • A. ZAG
    ZAG is the commonly used abbreviation for Zagłębie Lubin, a professional football club based in Lubin, Poland.
  • B. ZAZ
    ZAZ is the IATA airport code for Zaragoza Airport, a major civilian and military airfield serving the city of Zaragoza in northeastern Spain.
  • C. ZAD
    ZAD is the IATA airport code for Zadar Airport, which serves the coastal city of Zadar in Croatia.
  • D. ZG
    ZG is the vehicle registration code used on license plates for the city of Zagreb, the capital of Croatia.
  • E. ZA
    ZA is the ISO 3166-1 alpha-2 country code for South Africa.
  • 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: ZAG
Triple: [Zagreb Franjo Tuđman Airport, IATAcode, ZAG]
Generated description
ZAG is the three-letter IATA airport code for Zagreb Franjo Tuđman Airport, the main international airport serving Croatia’s capital city, Zagreb.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ZAG
Target entity description: ZAG is the three-letter IATA airport code for Zagreb Franjo Tuđman Airport, the main international airport serving Croatia’s capital city, Zagreb.
  • A. ZAG
    ZAG is the commonly used abbreviation for Zagłębie Lubin, a professional football club based in Lubin, Poland.
  • B. ZAZ
    ZAZ is the IATA airport code for Zaragoza Airport, a major civilian and military airfield serving the city of Zaragoza in northeastern Spain.
  • C. ZAD
    ZAD is the IATA airport code for Zadar Airport, which serves the coastal city of Zadar in Croatia.
  • D. ZG
    ZG is the vehicle registration code used on license plates for the city of Zagreb, the capital of Croatia.
  • E. ZA
    ZA is the ISO 3166-1 alpha-2 country code for South Africa.
  • 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_69c6884f3db4819080ad65da69386206 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6da606328819095eb852f7a0842dc completed March 27, 2026, 7:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7515509148190b5739cdf8cd7a28a completed March 28, 2026, 3:56 a.m.
NEDg Description generation batch_69c752c9b3d08190960d3c1aa88a93a7 completed March 28, 2026, 4:02 a.m.
NED2 Entity disambiguation (via description) batch_69c7537ea24c819081bb672d43d4a373 completed March 28, 2026, 4:05 a.m.
Created at: March 27, 2026, 2:27 p.m.