Triple

T4244917
Position Surface form Disambiguated ID Type / Status
Subject University of Wrocław E95504 entity
Predicate hasAbbreviation P43 FINISHED
Object UWr
UWr is the commonly used abbreviation for the University of Wrocław, a major public research university located in Wrocław, Poland.
 E424942 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: UWr | Statement: [University of Wrocław, hasAbbreviation, UWr]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: UWr
Context triple: [University of Wrocław, hasAbbreviation, UWr]
  • 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 a common abbreviation for the University of Wisconsin, whose athletic teams are known as the Wisconsin Badgers.
  • C. UW
    UW is the commonly used abbreviation for the University of Warsaw, a major public research university in Poland’s capital city.
  • D. UW
    UW is the University of Wyoming, a public land-grant research university located in Laramie, Wyoming.
  • E. ULM
    ULM is a public university in Monroe, Louisiana, known for its academic programs, research initiatives, and Warhawks athletic teams.
  • 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: UWr
Triple: [University of Wrocław, hasAbbreviation, UWr]
Generated description
UWr is the commonly used abbreviation for the University of Wrocław, a major public research university located in Wrocław, Poland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: UWr
Target entity description: UWr is the commonly used abbreviation for the University of Wrocław, a major public research university located in Wrocław, Poland.
  • 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 a common abbreviation for the University of Wisconsin, whose athletic teams are known as the Wisconsin Badgers.
  • C. UW
    UW is the commonly used abbreviation for the University of Warsaw, a major public research university in Poland’s capital city.
  • D. UW
    UW is the University of Wyoming, a public land-grant research university located in Laramie, Wyoming.
  • E. ULM
    ULM is a public university in Monroe, Louisiana, known for its academic programs, research initiatives, and Warhawks athletic teams.
  • 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_69b3453d91548190b4d4ef8fe52aa2ac completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34e8c42e88190b309a1ef7f6529ac completed March 12, 2026, 11:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5a876a8dc8190b79d7a3d5eec5609 completed March 14, 2026, 6:27 p.m.
NEDg Description generation batch_69b5a925b8e881908338dc0620b18734 completed March 14, 2026, 6:29 p.m.
NED2 Entity disambiguation (via description) batch_69b5ad224c848190b1ce76d61fc1d564 completed March 14, 2026, 6:46 p.m.
Created at: March 12, 2026, 11:05 p.m.