Triple

T22677544
Position Surface form Disambiguated ID Type / Status
Subject João Pessoa International Airport E560384 entity
Predicate ICAOcode P419 FINISHED
Object SBJP
SBJP is the ICAO airport code for João Pessoa International Airport, a commercial airport serving the city of João Pessoa in northeastern Brazil.
 E1549010 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: SBJP | Statement: [João Pessoa International Airport, ICAOcode, SBJP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SBJP
Context triple: [João Pessoa International Airport, ICAOcode, SBJP]
  • A. SBJ
    SBJ is the abbreviation for the Statistics Bureau of Japan, the government agency responsible for producing and managing Japan’s official statistical data.
  • B. BSJ
    BSJ is the National Rail station code for Bedford St Johns railway station in Bedford, England.
  • C. JBP
    JBP is the station code for Jabalpur Junction, a major railway hub in the Indian state of Madhya Pradesh.
  • D. SBRJ
    SBRJ is the ICAO airport code for Santos Dumont Airport, a major domestic airport located near downtown Rio de Janeiro, Brazil.
  • E. SBP
    SBP is the central bank of Pakistan, responsible for regulating the country’s monetary and credit system and ensuring financial stability.
  • 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: SBJP
Triple: [João Pessoa International Airport, ICAOcode, SBJP]
Generated description
SBJP is the ICAO airport code for João Pessoa International Airport, a commercial airport serving the city of João Pessoa in northeastern Brazil.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SBJP
Target entity description: SBJP is the ICAO airport code for João Pessoa International Airport, a commercial airport serving the city of João Pessoa in northeastern Brazil.
  • A. SBJ
    SBJ is the abbreviation for the Statistics Bureau of Japan, the government agency responsible for producing and managing Japan’s official statistical data.
  • B. BSJ
    BSJ is the National Rail station code for Bedford St Johns railway station in Bedford, England.
  • C. JBP
    JBP is the station code for Jabalpur Junction, a major railway hub in the Indian state of Madhya Pradesh.
  • D. SBRJ
    SBRJ is the ICAO airport code for Santos Dumont Airport, a major domestic airport located near downtown Rio de Janeiro, Brazil.
  • E. SBP
    SBP is the central bank of Pakistan, responsible for regulating the country’s monetary and credit system and ensuring financial stability.
  • 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_69e2454bfd00819099115715a22cb057 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1785d93e48190b37d11642b0cb123 completed April 29, 2026, 3:17 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b73f115cc819085e82dfa9f32ffa8 completed May 18, 2026, 8:17 p.m.
NEDg Description generation batch_6a0b752363a48190af3733c8ca995c25 completed May 18, 2026, 8:22 p.m.
NED2 Entity disambiguation (via description) batch_6a0b7601fda88190bbfa04e7eb240f65 completed May 18, 2026, 8:26 p.m.
Created at: April 17, 2026, 3:11 p.m.