Triple

T8062031
Position Surface form Disambiguated ID Type / Status
Subject University of Applied Sciences Karlsruhe E188146 entity
Predicate shortName P43 FINISHED
Object HsKA
HsKA is the abbreviated name of the University of Applied Sciences Karlsruhe, a German institution offering practice-oriented higher education in engineering, business, and related fields.
 E709405 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: HsKA | Statement: [University of Applied Sciences Karlsruhe, shortName, HsKA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HsKA
Context triple: [University of Applied Sciences Karlsruhe, shortName, HsKA]
  • A. KHS
    KHS is an Indian government institution dedicated to the promotion, teaching, and research of the Hindi language.
  • B. HSH
    HSH is the formal abbreviation used to address or refer to a person holding the noble style "His Serene Highness."
  • C. Khas
    Khas are an Indo-Aryan ethnic group originating from the Himalayan regions, historically influential in shaping the culture and language of modern Nepal.
  • D. HYS
    HYS is the National Rail station code for Hayes railway station in the London Borough of Bromley.
  • E. HAN
    HAN is the standard abbreviation used for the Hanshin Tigers, a professional baseball team in Japan's Nippon Professional Baseball league.
  • 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: HsKA
Triple: [University of Applied Sciences Karlsruhe, shortName, HsKA]
Generated description
HsKA is the abbreviated name of the University of Applied Sciences Karlsruhe, a German institution offering practice-oriented higher education in engineering, business, and related fields.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HsKA
Target entity description: HsKA is the abbreviated name of the University of Applied Sciences Karlsruhe, a German institution offering practice-oriented higher education in engineering, business, and related fields.
  • A. KHS
    KHS is an Indian government institution dedicated to the promotion, teaching, and research of the Hindi language.
  • B. HSH
    HSH is the formal abbreviation used to address or refer to a person holding the noble style "His Serene Highness."
  • C. Khas
    Khas are an Indo-Aryan ethnic group originating from the Himalayan regions, historically influential in shaping the culture and language of modern Nepal.
  • D. HYS
    HYS is the National Rail station code for Hayes railway station in the London Borough of Bromley.
  • E. HAN
    HAN is the standard abbreviation used for the Hanshin Tigers, a professional baseball team in Japan's Nippon Professional Baseball league.
  • 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_69ca82b2f68881908c50560697e210da completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3fcd7bcc8190b0a629a813846f13 completed March 31, 2026, 3:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc63da3bd08190894b2f4c977167c0 completed April 1, 2026, 12:16 a.m.
NEDg Description generation batch_69cc651c5f788190908c6d84c58cba0f completed April 1, 2026, 12:21 a.m.
NED2 Entity disambiguation (via description) batch_69cc6649d2348190996802140b455348 completed April 1, 2026, 12:26 a.m.
Created at: March 30, 2026, 5:26 p.m.