Triple

T5151414
Position Surface form Disambiguated ID Type / Status
Subject LAB University of Applied Sciences E116202 entity
Predicate shortName P43 FINISHED
Object LAB
LAB is a Finnish university of applied sciences offering practice-oriented higher education and research in fields such as business, technology, design, and health.
 E496996 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: LAB | Statement: [LAB University of Applied Sciences, shortName, LAB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LAB
Context triple: [LAB University of Applied Sciences, shortName, LAB]
  • A. LB
    LB is the vehicle registration code for the Ludwigsburg district in the Stuttgart administrative region of Baden-Württemberg, Germany.
  • B. LB
    LB is the former New York Stock Exchange ticker symbol for L Brands, the American retail company that owned brands such as Victoria’s Secret and Bath & Body Works.
  • C. LB
    LB is the two-letter ISO 3166-1 alpha-2 country code representing Lebanon.
  • D. LBA
    LBA is the IATA airport code for Leeds Bradford Airport, a regional international airport serving the cities of Leeds and Bradford in West Yorkshire, England.
  • E. LEAB
    LEAB is the ICAO airport code assigned to Albacete Air Base in Spain.
  • 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: LAB
Triple: [LAB University of Applied Sciences, shortName, LAB]
Generated description
LAB is a Finnish university of applied sciences offering practice-oriented higher education and research in fields such as business, technology, design, and health.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LAB
Target entity description: LAB is a Finnish university of applied sciences offering practice-oriented higher education and research in fields such as business, technology, design, and health.
  • A. LB
    LB is the former New York Stock Exchange ticker symbol for L Brands, the American retail company that owned brands such as Victoria’s Secret and Bath & Body Works.
  • B. LB
    LB is the vehicle registration code for the Ludwigsburg district in the Stuttgart administrative region of Baden-Württemberg, Germany.
  • C. LB
    LB is the two-letter ISO 3166-1 alpha-2 country code representing Lebanon.
  • D. LBA
    LBA is the IATA airport code for Leeds Bradford Airport, a regional international airport serving the cities of Leeds and Bradford in West Yorkshire, England.
  • E. LEAB
    LEAB is the ICAO airport code assigned to Albacete Air Base in Spain.
  • 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_69bd445d94788190b72e2cc563120995 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd78d965548190b09f574acf3b9b1a completed March 20, 2026, 4:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69bed004538c81908fac258ea99f7e63 completed March 21, 2026, 5:06 p.m.
NEDg Description generation batch_69bed07d478c8190aac215cb05bedae0 completed March 21, 2026, 5:08 p.m.
NED2 Entity disambiguation (via description) batch_69bed0d56af481908a3fb0693f151fb3 completed March 21, 2026, 5:09 p.m.
Created at: March 20, 2026, 1:44 p.m.