Triple

T5559415
Position Surface form Disambiguated ID Type / Status
Subject Sanaʽa International Airport E145727 entity
Predicate hasICAOCode P419 FINISHED
Object OYSN
OYSN is the ICAO airport code for Sanaʽa International Airport, the main airport serving Yemen’s capital city.
 E532281 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: OYSN | Statement: [Sanaʽa International Airport, hasICAOCode, OYSN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: OYSN
Context triple: [Sanaʽa International Airport, hasICAOCode, OYSN]
  • A. OY
    OY is the official vehicle registration code assigned to Oyo State in southwestern Nigeria.
  • B. OZN
    OZN was a Polish political organization associated with the interwar Sanation regime, supporting its authoritarian and nationalist policies.
  • C. Oy
    Oy is a loyal, intelligent billy-bumbler companion to Roland Deschain’s ka-tet in Stephen King’s The Dark Tower series.
  • D. OCS
    OCS is a United States Marine Corps training program that evaluates and prepares prospective officers for commissioning.
  • E. OCS
    OCS (Online Charging System) is a real-time telecommunications billing platform that manages and rates service usage, often working with PCRF to enforce charging and policy decisions.
  • 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: OYSN
Triple: [Sanaʽa International Airport, hasICAOCode, OYSN]
Generated description
OYSN is the ICAO 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: OYSN
Target entity description: OYSN is the ICAO airport code for Sanaʽa International Airport, the main airport serving Yemen’s capital city.
  • A. OY
    OY is the official vehicle registration code assigned to Oyo State in southwestern Nigeria.
  • B. OZN
    OZN was a Polish political organization associated with the interwar Sanation regime, supporting its authoritarian and nationalist policies.
  • C. Oy
    Oy is a loyal, intelligent billy-bumbler companion to Roland Deschain’s ka-tet in Stephen King’s The Dark Tower series.
  • D. OCS
    OCS is a United States Marine Corps training program that evaluates and prepares prospective officers for commissioning.
  • E. OCS
    OCS (Online Charging System) is a real-time telecommunications billing platform that manages and rates service usage, often working with PCRF to enforce charging and policy decisions.
  • 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.