Triple

T4850228
Position Surface form Disambiguated ID Type / Status
Subject The Welding Institute E108395 entity
Predicate shortName P43 FINISHED
Object TWI
TWI is a leading UK-based research and technology organization specializing in welding, joining, and related engineering technologies for industry.
 E474914 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: TWI | Statement: [The Welding Institute, shortName, TWI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: TWI
Context triple: [The Welding Institute, shortName, TWI]
  • A. TWG
    TWG is the commonly used abbreviation for The World Games, an international multi-sport event featuring disciplines not contested in the Olympic Games.
  • B. TIJ
    TIJ is the IATA airport code for Tijuana International Airport in Tijuana, Mexico.
  • C. TWB
    TWB is the IATA airport code for Toowoomba City Aerodrome, a regional airport serving the city of Toowoomba in Queensland, Australia.
  • D. TI
    TI is a technology company best known for designing and manufacturing calculators, semiconductors, and various electronic components.
  • E. TUW
    TUW is the commonly used abbreviation for the Vienna University of Technology, a major technical and scientific research university in Vienna, Austria.
  • 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: TWI
Triple: [The Welding Institute, shortName, TWI]
Generated description
TWI is a leading UK-based research and technology organization specializing in welding, joining, and related engineering technologies for industry.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: TWI
Target entity description: TWI is a leading UK-based research and technology organization specializing in welding, joining, and related engineering technologies for industry.
  • A. TWG
    TWG is the commonly used abbreviation for The World Games, an international multi-sport event featuring disciplines not contested in the Olympic Games.
  • B. TIJ
    TIJ is the IATA airport code for Tijuana International Airport in Tijuana, Mexico.
  • C. TWB
    TWB is the IATA airport code for Toowoomba City Aerodrome, a regional airport serving the city of Toowoomba in Queensland, Australia.
  • D. TI
    TI is a technology company best known for designing and manufacturing calculators, semiconductors, and various electronic components.
  • E. TUW
    TUW is the commonly used abbreviation for the Vienna University of Technology, a major technical and scientific research university in Vienna, Austria.
  • 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_69bd440a89548190a5f14ba6da6b97dc completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6d1e5cf08190bd6b6a524748f170 completed March 20, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69be5cdefda8819095fbc04446bf32f5 completed March 21, 2026, 8:54 a.m.
NEDg Description generation batch_69be5dadcec88190bf9a272c4a9aef9a completed March 21, 2026, 8:58 a.m.
NED2 Entity disambiguation (via description) batch_69be6159ff7c8190baa116240f76dea5 completed March 21, 2026, 9:14 a.m.
Created at: March 20, 2026, 1:25 p.m.