Triple

T20454964
Position Surface form Disambiguated ID Type / Status
Subject Osmani International Airport E501750 entity
Predicate ICAOcode P419 FINISHED
Object VGSY
VGSY is the ICAO airport code for Osmani International Airport in Sylhet, Bangladesh.
E1432395 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: VGSY | Statement: [Osmani International Airport, ICAOcode, VGSY]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: VGSY
Context triple: [Osmani International Airport, ICAOcode, VGSY]
  • A. LGSY
    LGSY is the ICAO airport code for Skyros Island National Airport in Greece.
  • B. VGN
    VGN (Verkehrsverbund Großraum Nürnberg) is the public transport association that coordinates and manages integrated ticketing and services across the greater Nuremberg metropolitan area in Germany.
  • C. VG AS
    VG AS is a Norwegian media company best known for publishing Verdens Gang (VG), one of Norway’s largest and most influential newspapers and news websites.
  • D. SGY
    SGY is the IATA airport code for Skagway Airport, a small public airport serving the town of Skagway in southeastern Alaska, United States.
  • E. GVSV
    GVSV is the ICAO airport code for Cesária Évora Airport on the island of São Vicente in Cape Verde.
  • 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: VGSY
Triple: [Osmani International Airport, ICAOcode, VGSY]
Generated description
VGSY is the ICAO airport code for Osmani International Airport in Sylhet, Bangladesh.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: VGSY
Target entity description: VGSY is the ICAO airport code for Osmani International Airport in Sylhet, Bangladesh.
  • A. LGSY
    LGSY is the ICAO airport code for Skyros Island National Airport in Greece.
  • B. VGN
    VGN (Verkehrsverbund Großraum Nürnberg) is the public transport association that coordinates and manages integrated ticketing and services across the greater Nuremberg metropolitan area in Germany.
  • C. VG AS
    VG AS is a Norwegian media company best known for publishing Verdens Gang (VG), one of Norway’s largest and most influential newspapers and news websites.
  • D. SGY
    SGY is the IATA airport code for Skagway Airport, a small public airport serving the town of Skagway in southeastern Alaska, United States.
  • E. GVSV
    GVSV is the ICAO airport code for Cesária Évora Airport on the island of São Vicente in Cape Verde.
  • 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_69e0b4ad4940819098cf2ff6413574e5 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e696a0dd188190ab6cbb387d9c0c1d completed April 20, 2026, 9:12 p.m.
NED1 Entity disambiguation (via context triple) batch_6a088b0e1d308190abb75555b9d20fd7 completed May 16, 2026, 3:19 p.m.
NEDg Description generation batch_6a088be79cd0819092da701d6d3d2a8a completed May 16, 2026, 3:23 p.m.
NED2 Entity disambiguation (via description) batch_6a088c7e46e48190b890f319ba4f2492 completed May 16, 2026, 3:25 p.m.
Created at: April 16, 2026, 11:32 a.m.