Triple

T16830975
Position Surface form Disambiguated ID Type / Status
Subject Fez–Saïss Airport E409146 entity
Predicate ICAOcode P419 FINISHED
Object GMFF
GMFF is the ICAO airport code for Fez–Saïss Airport, the main international airport serving the city of Fez in Morocco.
 E1235587 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: GMFF | Statement: [Fez–Saïss Airport, ICAOcode, GMFF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GMFF
Context triple: [Fez–Saïss Airport, ICAOcode, GMFF]
  • A. GFF
    GFF is the commonly used abbreviation for the Georgian Football Federation, the governing body of football in Georgia.
  • B. GFF
    GFF is the IATA airport code for Griffith Airport, a regional airport serving Griffith in New South Wales, Australia.
  • C. GSFA
    GSFA, formerly known as the Graduate School of Fine Arts at the University of Pennsylvania, was the university’s historic graduate division for architecture, landscape architecture, planning, and fine arts before being rebranded as the School of Design.
  • D. GF
    GF is the vehicle registration code used on license plates for the district of Gifhorn in Lower Saxony, Germany.
  • E. GF
    GF is the two-letter ISO 3166-1 alpha-2 country code assigned to French Guiana.
  • 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: GMFF
Triple: [Fez–Saïss Airport, ICAOcode, GMFF]
Generated description
GMFF is the ICAO airport code for Fez–Saïss Airport, the main international airport serving the city of Fez in Morocco.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GMFF
Target entity description: GMFF is the ICAO airport code for Fez–Saïss Airport, the main international airport serving the city of Fez in Morocco.
  • A. GFF
    GFF is the commonly used abbreviation for the Georgian Football Federation, the governing body of football in Georgia.
  • B. GFF
    GFF is the IATA airport code for Griffith Airport, a regional airport serving Griffith in New South Wales, Australia.
  • C. GSFA
    GSFA, formerly known as the Graduate School of Fine Arts at the University of Pennsylvania, was the university’s historic graduate division for architecture, landscape architecture, planning, and fine arts before being rebranded as the School of Design.
  • D. GF
    GF is the vehicle registration code used on license plates for the district of Gifhorn in Lower Saxony, Germany.
  • E. GF
    GF is the vehicle registration code assigned to the district that includes the Austrian town of Deutsch-Wagram.
  • 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_69d883952b048190887740a980b712ed completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b317af8c8190a09cb6d60d28e342 completed April 18, 2026, 4:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b2a2a5348190b14af8ab88a281b7 completed May 10, 2026, 4:30 p.m.
NEDg Description generation batch_6a00b475236c8190a345b4c8d3c6cfcf completed May 10, 2026, 4:38 p.m.
NED2 Entity disambiguation (via description) batch_6a00b6dfbf448190b41bb7d103ddfc0a completed May 10, 2026, 4:48 p.m.
Created at: April 10, 2026, 5:23 a.m.