Triple

T14148816
Position Surface form Disambiguated ID Type / Status
Subject Maputo International Airport E350620 entity
Predicate IATAcode P418 FINISHED
Object MPM
MPM is the IATA airport code for Maputo International Airport, the main international gateway to Maputo, Mozambique.
E1081718 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: MPM | Statement: [Maputo International Airport, IATAcode, MPM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MPM
Context triple: [Maputo International Airport, IATAcode, MPM]
  • A. MPM-10
    MPM-10 is a modern rubber-tired metro train model used on the Montreal Metro, designed to increase capacity, comfort, and energy efficiency.
  • B. MMP
    MMP is a hybrid electoral system that combines single-member district representation with proportional party lists to align a legislature’s overall seat distribution with parties’ share of the vote.
  • C. MMPS
    MMPS is the ICAO airport code assigned to Puerto Escondido International Airport in Oaxaca, Mexico.
  • D. MPS
    MPS (Metal Performance Shaders) is an Apple framework that provides highly optimized GPU-accelerated compute and graphics shaders for tasks like image processing and machine learning on Apple devices.
  • E. MPS
    MPS is a language workbench and integrated development environment by JetBrains designed for creating and working with domain-specific languages using projectional editing.
  • 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: MPM
Triple: [Maputo International Airport, IATAcode, MPM]
Generated description
MPM is the IATA airport code for Maputo International Airport, the main international gateway to Maputo, Mozambique.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MPM
Target entity description: MPM is the IATA airport code for Maputo International Airport, the main international gateway to Maputo, Mozambique.
  • A. MPM-10
    MPM-10 is a modern rubber-tired metro train model used on the Montreal Metro, designed to increase capacity, comfort, and energy efficiency.
  • B. MMP
    MMP is a hybrid electoral system that combines single-member district representation with proportional party lists to align a legislature’s overall seat distribution with parties’ share of the vote.
  • C. MMPS
    MMPS is the ICAO airport code assigned to Puerto Escondido International Airport in Oaxaca, Mexico.
  • D. MPS
    MPS is a leading German research institute specializing in the study of the Sun and the solar system, operating under the Max Planck Society.
  • E. MPS
    MPS is a language workbench and integrated development environment by JetBrains designed for creating and working with domain-specific languages using projectional editing.
  • 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_69d827865f608190b311820428ae027b completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61237ef481909374c1f68a2370b7 completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcdf205c788190920b5055f9fe63a8 completed May 7, 2026, 6:51 p.m.
NEDg Description generation batch_69fce266b2a08190998f04913064e43f completed May 7, 2026, 7:05 p.m.
NED2 Entity disambiguation (via description) batch_69fce2cd8cb481908e3e5a421e732948 completed May 7, 2026, 7:06 p.m.
Created at: April 10, 2026, 12:55 a.m.