Triple

T459627
Position Surface form Disambiguated ID Type / Status
Subject Karolinska Institute E7307 entity
Predicate abbreviation P43 FINISHED
Object KI
KI is the abbreviation for the Karolinska Institute, a renowned Swedish medical university known for its leading research and role in selecting Nobel laureates in Physiology or Medicine.
 E58171 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: KI | Statement: [Karolinska Institute, abbreviation, KI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KI
Context triple: [Karolinska Institute, abbreviation, KI]
  • A. KC
    KC is a common shorthand nickname for Kansas City, Missouri, a major Midwestern U.S. city known for its jazz heritage, barbecue, and sports teams.
  • B. kes
    Kes is the title given to the traditional religious leaders and priests of the Ethiopian Jewish (Beta Israel) community.
  • C. KP
    KP is the commonly used abbreviation for Khyber Pakhtunkhwa, a province in northwestern Pakistan known for its mountainous terrain and diverse ethnic communities.
  • D. KG
    KG is the post-nominal abbreviation used by Knights of the Order of the Garter, the highest order of chivalry in the United Kingdom.
  • E. KG
    KG is the widely used nickname of Kevin Garnett, a Hall of Fame NBA forward known for his intensity, defensive prowess, and versatility.
  • 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: KI
Triple: [Karolinska Institute, abbreviation, KI]
Generated description
KI is the abbreviation for the Karolinska Institute, a renowned Swedish medical university known for its leading research and role in selecting Nobel laureates in Physiology or Medicine.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KI
Target entity description: KI is the abbreviation for the Karolinska Institute, a renowned Swedish medical university known for its leading research and role in selecting Nobel laureates in Physiology or Medicine.
  • A. KC
    KC is a common shorthand nickname for Kansas City, Missouri, a major Midwestern U.S. city known for its jazz heritage, barbecue, and sports teams.
  • B. kes
    Kes is the title given to the traditional religious leaders and priests of the Ethiopian Jewish (Beta Israel) community.
  • C. KP
    KP is the commonly used abbreviation for Khyber Pakhtunkhwa, a province in northwestern Pakistan known for its mountainous terrain and diverse ethnic communities.
  • D. KG
    KG is the widely used nickname of Kevin Garnett, a Hall of Fame NBA forward known for his intensity, defensive prowess, and versatility.
  • E. KG
    KG is the post-nominal abbreviation used by Knights of the Order of the Garter, the highest order of chivalry in the United Kingdom.
  • 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_69a2e7e5c5bc8190a1dc8178218fba40 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2efa4a6208190a8243a0e14f84f52 completed Feb. 28, 2026, 1:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69a452947cd0819084fd885afce26da8 completed March 1, 2026, 2:52 p.m.
NEDg Description generation batch_69a4539f00008190a736df2fcaf3109a completed March 1, 2026, 2:56 p.m.
NED2 Entity disambiguation (via description) batch_69a4541cd02081908b8534b24d3933ff completed March 1, 2026, 2:58 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.