Triple

T2802575
Position Surface form Disambiguated ID Type / Status
Subject University of Helsinki E53179 entity
Predicate hasAbbreviation P43 FINISHED
Object UH
UH is the commonly used abbreviation for the University of Helsinki, a major research university in Finland.
E300410 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: UH | Statement: [University of Helsinki, hasAbbreviation, UH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UH
Context triple: [University of Helsinki, hasAbbreviation, UH]
  • A. UW
    UW is a leading Canadian public research university known for its strong engineering, computer science, and co-operative education programs.
  • B. UW
    UW is the commonly used abbreviation for the University of Warsaw, a major public research university in Poland’s capital city.
  • C. UAH
    UAH is the currency code for the Ukrainian hryvnia, the official national currency of Ukraine.
  • D. UAA
    UAA is the stock ticker symbol for Under Armour, an American sportswear and athletic apparel company traded on the New York Stock Exchange.
  • E. UCT
    UCT is a leading public research university in Cape Town, South Africa, renowned as one of Africa’s top higher education institutions.
  • 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: UH
Triple: [University of Helsinki, hasAbbreviation, UH]
Generated description
UH is the commonly used abbreviation for the University of Helsinki, a major research university in Finland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: UH
Target entity description: UH is the commonly used abbreviation for the University of Helsinki, a major research university in Finland.
  • A. UW
    UW is a leading Canadian public research university known for its strong engineering, computer science, and co-operative education programs.
  • B. UW
    UW is the commonly used abbreviation for the University of Warsaw, a major public research university in Poland’s capital city.
  • C. UAH
    UAH is the currency code for the Ukrainian hryvnia, the official national currency of Ukraine.
  • D. UAA
    UAA is the stock ticker symbol for Under Armour, an American sportswear and athletic apparel company traded on the New York Stock Exchange.
  • E. UCT
    UCT is a leading public research university in Cape Town, South Africa, renowned as one of Africa’s top higher education institutions.
  • 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_69ab495a90788190941b6917e1eca3a6 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abde12b33481908b276760a922db9c completed March 7, 2026, 8:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc671964c81908cff1cfbd70c3786 completed March 10, 2026, 7:21 a.m.
NEDg Description generation batch_69afcb9f73588190852ec35db9d9a7fd completed March 10, 2026, 7:43 a.m.
NED2 Entity disambiguation (via description) batch_69afcc0ddc188190a0d79974701556dd completed March 10, 2026, 7:45 a.m.
Created at: March 6, 2026, 9:58 p.m.