Triple

T4255791
Position Surface form Disambiguated ID Type / Status
Subject Bandaranaike International Airport E95970 entity
Predicate ICAOcode P419 FINISHED
Object VCBI
VCBI is the ICAO airport code for Bandaranaike International Airport, the main international gateway to Sri Lanka located near Colombo.
 E424705 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: VCBI | Statement: [Bandaranaike International Airport, ICAOcode, VCBI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: VCBI
Context triple: [Bandaranaike International Airport, ICAOcode, VCBI]
  • A. VIC
    VIC is the standard abbreviation for the Australian state of Victoria, commonly used in postal addresses and official contexts.
  • B. VIC
    VIC is the National Rail station code for London Victoria, a major central London railway terminus and Underground station.
  • C. VIBN
    VIBN is the ICAO airport code for Lal Bahadur Shastri International Airport serving Varanasi, India.
  • D. VCFA
    VCFA is a low-residency graduate arts college in Montpelier, Vermont, offering MFA and other advanced programs in disciplines such as writing, visual art, and music composition.
  • E. CVM
    CVM is the U.S. Food and Drug Administration’s Center for Veterinary Medicine, which regulates the safety and effectiveness of animal drugs and medicated feeds.
  • 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: VCBI
Triple: [Bandaranaike International Airport, ICAOcode, VCBI]
Generated description
VCBI is the ICAO airport code for Bandaranaike International Airport, the main international gateway to Sri Lanka located near Colombo.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: VCBI
Target entity description: VCBI is the ICAO airport code for Bandaranaike International Airport, the main international gateway to Sri Lanka located near Colombo.
  • A. VIC
    VIC is the standard abbreviation for the Australian state of Victoria, commonly used in postal addresses and official contexts.
  • B. VIC
    VIC is the National Rail station code for London Victoria, a major central London railway terminus and Underground station.
  • C. VIBN
    VIBN is the ICAO airport code for Lal Bahadur Shastri International Airport serving Varanasi, India.
  • D. VCFA
    VCFA is a low-residency graduate arts college in Montpelier, Vermont, offering MFA and other advanced programs in disciplines such as writing, visual art, and music composition.
  • E. CVM
    CVM is the U.S. Food and Drug Administration’s Center for Veterinary Medicine, which regulates the safety and effectiveness of animal drugs and medicated feeds.
  • 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_69b3453f759881909b91f01a1e82c036 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34ec1971c81908f7a72418efa8bcc completed March 12, 2026, 11:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5a88a68f081909e5bae5b0414f534 completed March 14, 2026, 6:27 p.m.
NEDg Description generation batch_69b5a94e637881909a20bb1df0cd5768 completed March 14, 2026, 6:30 p.m.
NED2 Entity disambiguation (via description) batch_69b5a9d9b28081909d7dc97b02209318 completed March 14, 2026, 6:32 p.m.
Created at: March 12, 2026, 11:06 p.m.