Triple

T10432707
Position Surface form Disambiguated ID Type / Status
Subject Makokou E245955 entity
Predicate airportIATACode P418 FINISHED
Object MKU E561002 NE FINISHED

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: MKU | Statement: [Makokou, airportIATACode, MKU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MKU
Context triple: [Makokou, airportIATACode, MKU]
  • A. MKU
    MKU is a public state university in Madurai, Tamil Nadu, India, known for its wide range of undergraduate, postgraduate, and research programs across arts, science, commerce, and management.
  • B. M-K
    M-K is the commonly used abbreviation for Morrison-Knudsen, a major American engineering and construction company known for large-scale infrastructure projects.
  • C. Mkuze chosen
    Mkuze is a small town in northern KwaZulu-Natal, South Africa, known as a gateway to nearby game reserves and wetlands.
  • D. MKA
    MKA is a structural and civil engineering firm known for designing high-rise and complex buildings worldwide.
  • E. MUCU
    MUCU is the ICAO airport code for Antonio Maceo International Airport in Santiago de Cuba, Cuba.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d381bf3dc08190bf35a2643e4e8f22 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4ea64f12c81909861d0d5165da2a2 completed April 7, 2026, 11:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69d87eb8c70481909b9320af15f2b5e9 completed April 10, 2026, 4:38 a.m.
Created at: April 6, 2026, 12:13 p.m.