Triple

T3933835
Position Surface form Disambiguated ID Type / Status
Subject University College Birmingham E90860 entity
Predicate shortName P43 FINISHED
Object UCB
UCB is a specialist university in Birmingham, England, known for its vocational and professional courses in areas such as hospitality, tourism, and culinary arts.
 E399679 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: UCB | Statement: [University College Birmingham, shortName, UCB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: UCB
Context triple: [University College Birmingham, shortName, UCB]
  • A. UCI
    UCI is the international governing body for cycling, responsible for overseeing competitive cycling events and setting global rules and standards for the sport.
  • B. UCE
    UCE is a major public university in Quito, Ecuador, recognized as one of the country’s oldest and most important higher education institutions.
  • C. UC
    UC is the final generation of the Holden Torana, a compact Australian car produced in the late 1970s.
  • D. UC
    UC is the commonly used abbreviation for Universal Credit, the United Kingdom’s main welfare benefit for people on a low income or out of work.
  • E. UC
    UC is a leading Chilean university, widely recognized for its academic excellence and strong influence in education, research, and public policy in Latin America.
  • 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: UCB
Triple: [University College Birmingham, shortName, UCB]
Generated description
UCB is a specialist university in Birmingham, England, known for its vocational and professional courses in areas such as hospitality, tourism, and culinary arts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: UCB
Target entity description: UCB is a specialist university in Birmingham, England, known for its vocational and professional courses in areas such as hospitality, tourism, and culinary arts.
  • A. UCI
    UCI is the international governing body for cycling, responsible for overseeing competitive cycling events and setting global rules and standards for the sport.
  • B. UCE
    UCE is a major public university in Quito, Ecuador, recognized as one of the country’s oldest and most important higher education institutions.
  • C. UC
    UC is the final generation of the Holden Torana, a compact Australian car produced in the late 1970s.
  • D. UC
    UC is the commonly used abbreviation for Universal Credit, the United Kingdom’s main welfare benefit for people on a low income or out of work.
  • E. UC
    UC is a leading Chilean university, widely recognized for its academic excellence and strong influence in education, research, and public policy in Latin America.
  • 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_69aed95f26e0819094b0e71974543a19 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeedcab1808190bf653f29062cdddb completed March 9, 2026, 3:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5288b7538819084936489226dd31f completed March 14, 2026, 9:21 a.m.
NEDg Description generation batch_69b529a1486881908ff348558199232b completed March 14, 2026, 9:25 a.m.
NED2 Entity disambiguation (via description) batch_69b52a43c6f081908366d9848728f98a completed March 14, 2026, 9:28 a.m.
Created at: March 9, 2026, 3:23 p.m.