Triple

T5559414
Position Surface form Disambiguated ID Type / Status
Subject Sanaʽa International Airport E145727 entity
Predicate hasIATACode P2569 FINISHED
Object SAH
SAH is the IATA airport code for Sanaʽa International Airport, the main airport serving Yemen’s capital city.
 E532280 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: SAH | Statement: [Sanaʽa International Airport, hasIATACode, SAH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SAH
Context triple: [Sanaʽa International Airport, hasIATACode, SAH]
  • A. TIA
    TIA is the IATA airport code for Tirana International Airport, the main air gateway to Albania’s capital city.
  • B. TIA
    TIA is a leading U.S.-based trade association that develops standards and advocates for companies in the global information and communications technology (ICT) and telecommunications industry.
  • C. SAHR
    SAHR is an automotive safety system developed by Saab that automatically moves the head restraint forward and upward during a rear-end collision to reduce the risk of whiplash injuries.
  • D. AHA
    AHA is the commonly used acronym for Atlantic Hockey, a collegiate ice hockey conference in the NCAA.
  • E. SAA
    SAA is the ICAO airline designator for South African Airways, the flag carrier airline of 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: SAH
Triple: [Sanaʽa International Airport, hasIATACode, SAH]
Generated description
SAH is the IATA airport code for Sanaʽa International Airport, the main airport serving Yemen’s capital city.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SAH
Target entity description: SAH is the IATA airport code for Sanaʽa International Airport, the main airport serving Yemen’s capital city.
  • A. TIA
    TIA is the IATA airport code for Tirana International Airport, the main air gateway to Albania’s capital city.
  • B. TIA
    TIA is a leading U.S.-based trade association that develops standards and advocates for companies in the global information and communications technology (ICT) and telecommunications industry.
  • C. SAHR
    SAHR is an automotive safety system developed by Saab that automatically moves the head restraint forward and upward during a rear-end collision to reduce the risk of whiplash injuries.
  • D. AHA
    AHA is the commonly used acronym for Atlantic Hockey, a collegiate ice hockey conference in the NCAA.
  • E. SAA
    SAA is the ICAO airline designator for South African Airways, the flag carrier airline of 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_69c008fcaf788190bafa02a1917ee73b completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c020167afc8190b0c518907cd0d99b completed March 22, 2026, 5 p.m.
NED1 Entity disambiguation (via context triple) batch_69c028424ddc8190869b530a8eb43f50 completed March 22, 2026, 5:34 p.m.
NEDg Description generation batch_69c0349f64c0819083b39d8b7960a393 completed March 22, 2026, 6:27 p.m.
NED2 Entity disambiguation (via description) batch_69c0354e95808190b4386e2796291dba completed March 22, 2026, 6:30 p.m.
Created at: March 22, 2026, 3:36 p.m.