Triple

T17422883
Position Surface form Disambiguated ID Type / Status
Subject Saint-Louis Airport E423661 entity
Predicate IATAcode P418 FINISHED
Object XLS
XLS is the three-letter IATA airport code assigned to Saint-Louis Airport in Senegal.
 E1267736 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: XLS | Statement: [Saint-Louis Airport, IATAcode, XLS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: XLS
Context triple: [Saint-Louis Airport, IATAcode, XLS]
  • A. SXC
    SXC is the stock ticker symbol for SunCoke Energy, Inc., a U.S.-based producer of coke used in steelmaking and a provider of related logistics services.
  • B. Excel
    Excel is a widely used spreadsheet software by Microsoft that enables data organization, analysis, visualization, and basic to advanced analytics through formulas, functions, and tools like PivotTables.
  • C. Excel
    Excel is a high-specification trim level of the Toyota Auris that offers upgraded comfort, technology, and styling features compared to lower trims.
  • D. Excello
    Excello is a small unincorporated community located in Macon County, Missouri, in the United States.
  • E. Office Open XML (ECMA-376)
    Office Open XML (ECMA-376) is a standardized, XML-based file format used primarily by Microsoft Office applications for representing word processing documents, spreadsheets, and presentations.
  • 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: XLS
Triple: [Saint-Louis Airport, IATAcode, XLS]
Generated description
XLS is the three-letter IATA airport code assigned to Saint-Louis Airport in Senegal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: XLS
Target entity description: XLS is the three-letter IATA airport code assigned to Saint-Louis Airport in Senegal.
  • A. SXC
    SXC is the stock ticker symbol for SunCoke Energy, Inc., a U.S.-based producer of coke used in steelmaking and a provider of related logistics services.
  • B. Excel
    Excel is a widely used spreadsheet software by Microsoft that enables data organization, analysis, visualization, and basic to advanced analytics through formulas, functions, and tools like PivotTables.
  • C. Excel
    Excel is a high-specification trim level of the Toyota Auris that offers upgraded comfort, technology, and styling features compared to lower trims.
  • D. Excello
    Excello is a small unincorporated community located in Macon County, Missouri, in the United States.
  • E. Office Open XML (ECMA-376)
    Office Open XML (ECMA-376) is a standardized, XML-based file format used primarily by Microsoft Office applications for representing word processing documents, spreadsheets, and presentations.
  • 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_69d889d88b6081908bada047f5b3ba51 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e44238b418819095c6a013d3ff3b17 completed April 19, 2026, 2:47 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01a80670bc8190aa8c7651e8973bb3 completed May 11, 2026, 9:57 a.m.
NEDg Description generation batch_6a01aa8b777c81909b8a4a5e790634e8 completed May 11, 2026, 10:08 a.m.
NED2 Entity disambiguation (via description) batch_6a01ab5a7a408190a457ddef4a0a7b09 completed May 11, 2026, 10:11 a.m.
Created at: April 10, 2026, 5:46 a.m.