Triple

T6539195
Position Surface form Disambiguated ID Type / Status
Subject Cap-Haïtien E168241 entity
Predicate airportIATA P418 FINISHED
Object CAP
CAP is the IATA airport code for Cap-Haïtien International Airport, serving the city of Cap-Haïtien in northern Haiti.
 E604078 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: CAP | Statement: [Cap-Haïtien, airportIATA, CAP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CAP
Context triple: [Cap-Haïtien, airportIATA, CAP]
  • A. CAP
    CAP is the European Union’s Common Agricultural Policy, a framework of subsidies and programs designed to support farmers, ensure food security, and manage rural development across member states.
  • B. CAP
    CAP is a professional certification that validates an individual's expertise in applying analytics to solve real-world business problems.
  • C. CAP
    CAP is the stock ticker symbol for Capgemini, a global consulting, technology services, and digital transformation company listed on the Euronext Paris exchange.
  • D. CAP
    CAP (Common Alerting Protocol) is an international XML-based data format used for exchanging public warnings and emergency alerts across different systems and networks.
  • E. CAP
    CAP is the commonly used acronym for the Central Arizona Project, a major canal system that delivers Colorado River water to central and southern Arizona.
  • 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: CAP
Triple: [Cap-Haïtien, airportIATA, CAP]
Generated description
CAP is the IATA airport code for Cap-Haïtien International Airport, serving the city of Cap-Haïtien in northern Haiti.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CAP
Target entity description: CAP is the IATA airport code for Cap-Haïtien International Airport, serving the city of Cap-Haïtien in northern Haiti.
  • A. CAP
    CAP is the European Union’s Common Agricultural Policy, a framework of subsidies and programs designed to support farmers, ensure food security, and manage rural development across member states.
  • B. CAP
    CAP is a professional certification that validates an individual's expertise in applying analytics to solve real-world business problems.
  • C. CAP
    CAP is the commonly used acronym for the Central Arizona Project, a major canal system that delivers Colorado River water to central and southern Arizona.
  • D. CAP
    CAP is the stock ticker symbol for Capgemini, a global consulting, technology services, and digital transformation company listed on the Euronext Paris exchange.
  • E. CAP
    CAP (Common Alerting Protocol) is an international XML-based data format used for exchanging public warnings and emergency alerts across different systems and networks.
  • 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_69c68a51564081909e93aee0dbd9cca3 completed March 27, 2026, 1:46 p.m.
NER Named-entity recognition batch_69c6add5d3848190a0d70dc4013ab756 completed March 27, 2026, 4:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6d53b861c81908adc984a3067d4ef completed March 27, 2026, 7:06 p.m.
NEDg Description generation batch_69c6d6745b40819083fbcb2a4063e34d completed March 27, 2026, 7:11 p.m.
NED2 Entity disambiguation (via description) batch_69c6d837a5248190b0afb39174ac3922 completed March 27, 2026, 7:19 p.m.
Created at: March 27, 2026, 1:50 p.m.