Triple

T1701973
Position Surface form Disambiguated ID Type / Status
Subject IMO Legal Committee E36786 entity
Predicate shortName P43 FINISHED
Object LEG
LEG is the International Maritime Organization’s Legal Committee, responsible for developing and maintaining international maritime law and liability conventions.
 E191682 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: LEG | Statement: [IMO Legal Committee, shortName, LEG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LEG
Context triple: [IMO Legal Committee, shortName, LEG]
  • A. LEX
    LEX is the abbreviation for the Léman Express, a cross-border commuter rail network serving the Greater Geneva region in Switzerland and France.
  • B. Le
    Le is a common Vietnamese surname shared by many notable figures in the country’s history and culture.
  • C. Lex
    Lex is a common shortened form of the given name Alexander, often used as a modern, informal nickname.
  • D. Lu
    Lu is the traditional abbreviation and historical name used to refer to China’s Shandong province.
  • E. LAS
    LAS is an abbreviation commonly used for the College of Liberal Arts and Sciences at many universities, encompassing a broad range of humanities, social sciences, and natural sciences disciplines.
  • 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: LEG
Triple: [IMO Legal Committee, shortName, LEG]
Generated description
LEG is the International Maritime Organization’s Legal Committee, responsible for developing and maintaining international maritime law and liability conventions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LEG
Target entity description: LEG is the International Maritime Organization’s Legal Committee, responsible for developing and maintaining international maritime law and liability conventions.
  • A. LEX
    LEX is the abbreviation for the Léman Express, a cross-border commuter rail network serving the Greater Geneva region in Switzerland and France.
  • B. Le
    Le is a common Vietnamese surname shared by many notable figures in the country’s history and culture.
  • C. Lex
    Lex is a common shortened form of the given name Alexander, often used as a modern, informal nickname.
  • D. Lu
    Lu is the traditional abbreviation and historical name used to refer to China’s Shandong province.
  • E. LAS
    LAS is an abbreviation commonly used for the College of Liberal Arts and Sciences at many universities, encompassing a broad range of humanities, social sciences, and natural sciences disciplines.
  • 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_69a886163dec8190859c514232a37a05 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa62d6c7c88190998ce97d65395280 completed March 6, 2026, 5:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad799f98e48190b9eaf6f5151f4c80 completed March 8, 2026, 1:29 p.m.
NEDg Description generation batch_69ad7a224d248190b0d1a7f70b76c164 completed March 8, 2026, 1:31 p.m.
NED2 Entity disambiguation (via description) batch_69ad7b4b4a208190966fa07a6f0d626e completed March 8, 2026, 1:36 p.m.
Created at: March 4, 2026, 7:30 p.m.