Triple

T2353915
Position Surface form Disambiguated ID Type / Status
Subject Robert Gabriel Mugabe International Airport E47510 entity
Predicate ICAOcode P419 FINISHED
Object FVHA
FVHA is the ICAO airport code for Robert Gabriel Mugabe International Airport in Harare, Zimbabwe.
 E257666 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: FVHA | Statement: [Robert Gabriel Mugabe International Airport, ICAOcode, FVHA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FVHA
Context triple: [Robert Gabriel Mugabe International Airport, ICAOcode, FVHA]
  • A. FHC
    FHC is the commonly used acronym and honorific referring to Fernando Henrique Cardoso, a prominent Brazilian sociologist and former president of Brazil.
  • B. FV
    FV is the IATA airline designator assigned to Rossiya Airlines, a Russian carrier based in Saint Petersburg.
  • C. HAVA
    HAVA is the commonly used acronym for the Help America Vote Act, a U.S. federal law enacted to improve the administration and security of elections.
  • D. HVF
    HVF is a data-focused startup and innovation lab created by entrepreneur Max Levchin to explore and build companies around large-scale data problems.
  • E. HVN
    HVN is the ICAO airline designator used to identify Vietnam Airlines in international aviation operations.
  • 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: FVHA
Triple: [Robert Gabriel Mugabe International Airport, ICAOcode, FVHA]
Generated description
FVHA is the ICAO airport code for Robert Gabriel Mugabe International Airport in Harare, Zimbabwe.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FVHA
Target entity description: FVHA is the ICAO airport code for Robert Gabriel Mugabe International Airport in Harare, Zimbabwe.
  • A. FHC
    FHC is the commonly used acronym and honorific referring to Fernando Henrique Cardoso, a prominent Brazilian sociologist and former president of Brazil.
  • B. FV
    FV is the IATA airline designator assigned to Rossiya Airlines, a Russian carrier based in Saint Petersburg.
  • C. HAVA
    HAVA is the commonly used acronym for the Help America Vote Act, a U.S. federal law enacted to improve the administration and security of elections.
  • D. HVF
    HVF is a data-focused startup and innovation lab created by entrepreneur Max Levchin to explore and build companies around large-scale data problems.
  • E. HVN
    HVN is the ICAO airline designator used to identify Vietnam Airlines in international aviation operations.
  • 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_69a88a1b678c8190bce986922ba60ce0 completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abc6fa6ecc8190821c9d5db341cf19 completed March 7, 2026, 6:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae9633ce3c81908581e7e0f8211ac1 completed March 9, 2026, 9:43 a.m.
NEDg Description generation batch_69ae971aa3bc8190b0b8b216106dca90 completed March 9, 2026, 9:47 a.m.
NED2 Entity disambiguation (via description) batch_69ae9795cf048190bc7a01ef86c12138 completed March 9, 2026, 9:49 a.m.
Created at: March 4, 2026, 7:54 p.m.