Triple

T689669
Position Surface form Disambiguated ID Type / Status
Subject SriLankan Airlines E13363 entity
Predicate ICAOcode P419 FINISHED
Object ALK
ALK is the ICAO airline designator used to identify SriLankan Airlines in international aviation operations.
E84981 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: ALK | Statement: [SriLankan Airlines, ICAOcode, ALK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ALK
Context triple: [SriLankan Airlines, ICAOcode, ALK]
  • A. Al
    Al is a common shortened form of given names such as Albert, Alan, or Alexander.
  • B. AL
    AL is the common abbreviation for the American League, one of the two major professional baseball leagues that make up Major League Baseball in the United States and Canada.
  • C. AK
    AK is the Polish abbreviation for the Home Army, the principal resistance movement in German-occupied Poland during World War II.
  • D. AO
    AO is the two-letter ISO 3166-1 alpha-2 country code representing Angola in international standards and systems.
  • E. AO
    AO is the commonly used abbreviation for the Administrative Office of the United States Courts, the federal agency that provides administrative support to the U.S. federal judiciary.
  • 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: ALK
Triple: [SriLankan Airlines, ICAOcode, ALK]
Generated description
ALK is the ICAO airline designator used to identify SriLankan Airlines in international aviation operations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ALK
Target entity description: ALK is the ICAO airline designator used to identify SriLankan Airlines in international aviation operations.
  • A. Al
    Al is a common shortened form of given names such as Albert, Alan, or Alexander.
  • B. AL
    AL is the common abbreviation for the American League, one of the two major professional baseball leagues that make up Major League Baseball in the United States and Canada.
  • C. AK
    AK is the Polish abbreviation for the Home Army, the principal resistance movement in German-occupied Poland during World War II.
  • D. AO
    AO is the two-letter ISO 3166-1 alpha-2 country code representing Angola in international standards and systems.
  • E. AO
    AO is the commonly used abbreviation for the Administrative Office of the United States Courts, the federal agency that provides administrative support to the U.S. federal judiciary.
  • 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_69a4933e0f98819097d22766c49b61b8 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a4a0ad379c81909003d35c63822780 completed March 1, 2026, 8:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5dca5b2688190bfe05a165c753211 completed March 2, 2026, 6:53 p.m.
NEDg Description generation batch_69a5ddeaef148190bb9877cee15959fd completed March 2, 2026, 6:58 p.m.
NED2 Entity disambiguation (via description) batch_69a5fea9df3481909331e3e382ad81ae completed March 2, 2026, 9:18 p.m.
Created at: March 1, 2026, 7:36 p.m.