Triple

T6665399
Position Surface form Disambiguated ID Type / Status
Subject State University of Haiti E151588 entity
Predicate abbreviation P43 FINISHED
Object UEH
UEH is the French acronym for the State University of Haiti, the country’s main public higher education institution.
 E608956 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: UEH | Statement: [State University of Haiti, abbreviation, UEH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: UEH
Context triple: [State University of Haiti, abbreviation, UEH]
  • A. UEW
    UEW is the commonly used abbreviation for the Wrocław University of Economics and Business, a major Polish institution specializing in economics, management, and related fields.
  • B. UHK
    UHK is a public university in Hradec Králové, Czech Republic, offering a range of academic programs and research activities across multiple faculties.
  • C. UEA
    UEA is the World Esperanto Association, the leading international organization dedicated to promoting and coordinating the global Esperanto movement.
  • D. UER
    UER is the French abbreviation for the European Broadcasting Union, an alliance of public service media organizations across Europe and beyond.
  • E. UH
    UH is a major public research university located in Houston, Texas, known for its diverse student body and strong programs in fields such as engineering, business, and the arts.
  • 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: UEH
Triple: [State University of Haiti, abbreviation, UEH]
Generated description
UEH is the French acronym for the State University of Haiti, the country’s main public higher education institution.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: UEH
Target entity description: UEH is the French acronym for the State University of Haiti, the country’s main public higher education institution.
  • A. UEW
    UEW is the commonly used abbreviation for the Wrocław University of Economics and Business, a major Polish institution specializing in economics, management, and related fields.
  • B. UHK
    UHK is a public university in Hradec Králové, Czech Republic, offering a range of academic programs and research activities across multiple faculties.
  • C. UEA
    UEA is the World Esperanto Association, the leading international organization dedicated to promoting and coordinating the global Esperanto movement.
  • D. UER
    UER is the French abbreviation for the European Broadcasting Union, an alliance of public service media organizations across Europe and beyond.
  • E. UH
    UH is a major public research university located in Houston, Texas, known for its diverse student body and strong programs in fields such as engineering, business, and the arts.
  • 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_69c687f71fc081909dbd45d6377f6045 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b09d97648190a254cabc0ffcb0dc completed March 27, 2026, 4:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6ef0e33308190995fcccf50d134c1 completed March 27, 2026, 8:56 p.m.
NEDg Description generation batch_69c6f0a3f0b481908dfe70d626277e8f completed March 27, 2026, 9:03 p.m.
NED2 Entity disambiguation (via description) batch_69c6f1a3995c8190b22766356b6e6bf8 completed March 27, 2026, 9:07 p.m.
Created at: March 27, 2026, 2:02 p.m.