Triple

T10258091
Position Surface form Disambiguated ID Type / Status
Subject Juan Santamaría International Airport E240525 entity
Predicate IATAcode P418 FINISHED
Object SJO
SJO is the IATA airport code for Juan Santamaría International Airport, the main international gateway serving San José, Costa Rica.
 E851596 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: SJO | Statement: [Juan Santamaría International Airport, IATAcode, SJO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SJO
Context triple: [Juan Santamaría International Airport, IATAcode, SJO]
  • A. SJO
    SJO is the ICAO airline designator assigned to Spring Airlines Japan, a Japanese low-cost carrier.
  • B. S.J.
    S.J. is the standard post-nominal abbreviation used to designate members of the Catholic religious order known as the Society of Jesus, or the Jesuits.
  • C. SJ
    SJ is Sweden’s primary state-owned passenger train operator, running long-distance and regional rail services across the country.
  • D. .sj
    .sj is the reserved country code top-level domain designated for Svalbard and Jan Mayen, territories of Norway, which is not actively used for general internet registrations.
  • E. SJC
    SJC is the abbreviation commonly used for the Massachusetts Supreme Judicial Court, the highest appellate court in the Commonwealth of Massachusetts.
  • 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: SJO
Triple: [Juan Santamaría International Airport, IATAcode, SJO]
Generated description
SJO is the IATA airport code for Juan Santamaría International Airport, the main international gateway serving San José, Costa Rica.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SJO
Target entity description: SJO is the IATA airport code for Juan Santamaría International Airport, the main international gateway serving San José, Costa Rica.
  • A. SJO
    SJO is the ICAO airline designator assigned to Spring Airlines Japan, a Japanese low-cost carrier.
  • B. S.J.
    S.J. is the standard post-nominal abbreviation used to designate members of the Catholic religious order known as the Society of Jesus, or the Jesuits.
  • C. SJ
    SJ is Sweden’s primary state-owned passenger train operator, running long-distance and regional rail services across the country.
  • D. .sj
    .sj is the reserved country code top-level domain designated for Svalbard and Jan Mayen, territories of Norway, which is not actively used for general internet registrations.
  • E. SJC
    SJC is the abbreviation commonly used for the Massachusetts Supreme Judicial Court, the highest appellate court in the Commonwealth of Massachusetts.
  • 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_69d381a7e198819090280d5ab885d59e completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d24de4588190b68fb3daa36dbd7d completed April 7, 2026, 9:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f7e9a9d48190865f047750d7bc6c completed April 9, 2026, 12:50 a.m.
NEDg Description generation batch_69d6fcabb5a08190a26c068163f48878 completed April 9, 2026, 1:11 a.m.
NED2 Entity disambiguation (via description) batch_69d6fd7212b88190b410b8e1cc6f56fd completed April 9, 2026, 1:14 a.m.
Created at: April 6, 2026, 11:31 a.m.