Triple

T9121483
Position Surface form Disambiguated ID Type / Status
Subject Pietermaritzburg Airport E218860 entity
Predicate ICAOcode P419 FINISHED
Object FAPM
FAPM is the ICAO airport code for Pietermaritzburg Airport in Pietermaritzburg, South Africa.
 E779558 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: FAPM | Statement: [Pietermaritzburg Airport, ICAOcode, FAPM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FAPM
Context triple: [Pietermaritzburg Airport, ICAOcode, FAPM]
  • A. FAPS
    FAPS is a professional honorific title signifying election as a Fellow of the American Physical Society in recognition of exceptional contributions to physics.
  • B. FAAPM
    FAAPM is a professional designation awarded to distinguished members of the American Association of Physicists in Medicine in recognition of significant contributions to the field of medical physics.
  • C. FPM
    FPM is the Fellow Programme in Management, a doctoral-level research program in management studies offered by the Indian Institutes of Management.
  • D. FAPSI
    FAPSI was a Russian government agency responsible for signals intelligence, secure communications, and information security, functioning as a successor to parts of the Soviet KGB.
  • E. FAP
    FAP is the acronym for the Peruvian Air Force, the aerial warfare branch of Peru’s armed forces.
  • 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: FAPM
Triple: [Pietermaritzburg Airport, ICAOcode, FAPM]
Generated description
FAPM is the ICAO airport code for Pietermaritzburg Airport in Pietermaritzburg, South Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FAPM
Target entity description: FAPM is the ICAO airport code for Pietermaritzburg Airport in Pietermaritzburg, South Africa.
  • A. FAPS
    FAPS is a professional honorific title signifying election as a Fellow of the American Physical Society in recognition of exceptional contributions to physics.
  • B. FAAPM
    FAAPM is a professional designation awarded to distinguished members of the American Association of Physicists in Medicine in recognition of significant contributions to the field of medical physics.
  • C. FPM
    FPM is the Fellow Programme in Management, a doctoral-level research program in management studies offered by the Indian Institutes of Management.
  • D. FAPSI
    FAPSI was a Russian government agency responsible for signals intelligence, secure communications, and information security, functioning as a successor to parts of the Soviet KGB.
  • E. FAP
    FAP is the acronym for the Peruvian Air Force, the aerial warfare branch of Peru’s armed forces.
  • 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_69ca83dddd548190983b96c664f7f367 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca8b32ba88190b2b4406c7b905cca completed April 1, 2026, 5:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0308ff628819083f02bf71eb40c5b completed April 3, 2026, 9:26 p.m.
NEDg Description generation batch_69d0318ef52c8190bfa0bef6a8d41daa completed April 3, 2026, 9:30 p.m.
NED2 Entity disambiguation (via description) batch_69d03571c4648190bd546152c61c55a5 completed April 3, 2026, 9:47 p.m.
Created at: March 30, 2026, 7:17 p.m.