Triple

T23022911
Position Surface form Disambiguated ID Type / Status
Subject Aero Mongolia E573215 entity
Predicate ICAOCode P419 FINISHED
Object MNG NE NERFINISHED

How this triple was built (2 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: MNG | Statement: [Aero Mongolia, ICAOCode, MNG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MNG
Context triple: [Aero Mongolia, ICAOCode, MNG]
  • A. MNG chosen
    MNG is the three-letter FIFA country code representing the Mongolia national football team in international competitions.
  • B. DNG
    DNG (Digital Negative) is an open, publicly documented raw image file format developed by Adobe for long-term archival and broad compatibility of digital photographs.
  • C. MPIMG
    MPIMG is a leading research institute of the Max Planck Society focused on advancing molecular genetics and genomics.
  • D. MoPNG
    MoPNG is the Indian government ministry responsible for overseeing the exploration, production, refining, distribution, and marketing of petroleum and natural gas in India.
  • E. PNG
    PNG is the three-letter ISO 3166-1 alpha-3 country code representing Papua New Guinea.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245b821008190b0e09cb02092aae1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183ea23088190b2f42d9bf01514ac completed April 29, 2026, 4:07 a.m.
Created at: April 17, 2026, 3:52 p.m.