Triple

T6839364
Position Surface form Disambiguated ID Type / Status
Subject Abdul Rachman Saleh Airport E157530 entity
Predicate IATAcode P418 FINISHED
Object MLG
MLG is the IATA airport code for Abdul Rachman Saleh Airport serving the Malang area in East Java, Indonesia.
 E622214 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: MLG | Statement: [Abdul Rachman Saleh Airport, IATAcode, MLG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MLG
Context triple: [Abdul Rachman Saleh Airport, IATAcode, MLG]
  • A. MLN
    MLN is the IATA airport code for Melilla Airport, which serves the Spanish autonomous city of Melilla on the north coast of Africa.
  • B. 3d MLG
    3d MLG is a United States Marine Corps logistics unit that provides comprehensive combat service support to Marine Air-Ground Task Forces, primarily in the Indo-Pacific region.
  • C. 2d MLG
    2d MLG is a major logistics formation of the United States Marine Corps responsible for providing supply, maintenance, transportation, and support services to Marine forces.
  • D. MCWL
    MCWL is the U.S. Marine Corps Warfighting Laboratory, responsible for developing, testing, and integrating innovative concepts and technologies to enhance future Marine Corps combat capabilities.
  • E. MC
    MC is the official abbreviation for NATO’s highest military authority, the NATO Military Committee.
  • 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: MLG
Triple: [Abdul Rachman Saleh Airport, IATAcode, MLG]
Generated description
MLG is the IATA airport code for Abdul Rachman Saleh Airport serving the Malang area in East Java, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MLG
Target entity description: MLG is the IATA airport code for Abdul Rachman Saleh Airport serving the Malang area in East Java, Indonesia.
  • A. MLN
    MLN is the IATA airport code for Melilla Airport, which serves the Spanish autonomous city of Melilla on the north coast of Africa.
  • B. 3d MLG
    3d MLG is a United States Marine Corps logistics unit that provides comprehensive combat service support to Marine Air-Ground Task Forces, primarily in the Indo-Pacific region.
  • C. 2d MLG
    2d MLG is a major logistics formation of the United States Marine Corps responsible for providing supply, maintenance, transportation, and support services to Marine forces.
  • D. MCWL
    MCWL is the U.S. Marine Corps Warfighting Laboratory, responsible for developing, testing, and integrating innovative concepts and technologies to enhance future Marine Corps combat capabilities.
  • E. MC
    MC is the official abbreviation for NATO’s highest military authority, the NATO Military Committee.
  • 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_69c6882c53608190b99aebef079b23bd completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d6b2ee248190991c3e827be75bb7 completed March 27, 2026, 7:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69c724047c048190b1cf6901f1577e01 completed March 28, 2026, 12:42 a.m.
NEDg Description generation batch_69c724d7f0308190abb494ea663ceeb9 completed March 28, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_69c72568866c8190bf88a02e566d5c3a completed March 28, 2026, 12:48 a.m.
Created at: March 27, 2026, 2:19 p.m.