Triple

T414732
Position Surface form Disambiguated ID Type / Status
Subject Robert Koch E9566 entity
Predicate discovered P412 FINISHED
Object Mycobacterium tuberculosis
Mycobacterium tuberculosis is the pathogenic bacterial species that causes most cases of human tuberculosis, primarily affecting the lungs and spreading through airborne transmission.
E52537 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: Mycobacterium tuberculosis | Statement: [Robert Koch, discovered, Mycobacterium tuberculosis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mycobacterium tuberculosis
Context triple: [Robert Koch, discovered, Mycobacterium tuberculosis]
  • A. Campylobacter
    Campylobacter is a genus of bacteria that commonly causes foodborne gastrointestinal infections in humans, often associated with undercooked poultry.
  • B. Nourse
    Nourse is a surname and variant spelling of "Nurse," historically associated with English-speaking families and occasionally used as a place or business name.
  • C. Phytophthora infestans
    Phytophthora infestans is a plant-pathogenic oomycete best known for causing potato late blight, the disease responsible for the devastating 19th-century Irish Great Famine.
  • D. TMV
    TMV is the stock ticker symbol under which TeamViewer, a global provider of remote connectivity and remote access software, is traded on financial markets.
  • E. Monera
    Monera is a former biological kingdom that comprised all prokaryotic, single-celled organisms such as bacteria and archaea, distinguished by their lack of a true nucleus and membrane-bound organelles.
  • 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: Mycobacterium tuberculosis
Triple: [Robert Koch, discovered, Mycobacterium tuberculosis]
Generated description
Mycobacterium tuberculosis is the pathogenic bacterial species that causes most cases of human tuberculosis, primarily affecting the lungs and spreading through airborne transmission.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mycobacterium tuberculosis
Target entity description: Mycobacterium tuberculosis is the pathogenic bacterial species that causes most cases of human tuberculosis, primarily affecting the lungs and spreading through airborne transmission.
  • A. Campylobacter
    Campylobacter is a genus of bacteria that commonly causes foodborne gastrointestinal infections in humans, often associated with undercooked poultry.
  • B. Nourse
    Nourse is a surname and variant spelling of "Nurse," historically associated with English-speaking families and occasionally used as a place or business name.
  • C. Phytophthora infestans
    Phytophthora infestans is a plant-pathogenic oomycete best known for causing potato late blight, the disease responsible for the devastating 19th-century Irish Great Famine.
  • D. TMV
    TMV is the stock ticker symbol under which TeamViewer, a global provider of remote connectivity and remote access software, is traded on financial markets.
  • E. Monera
    Monera is a former biological kingdom that comprised all prokaryotic, single-celled organisms such as bacteria and archaea, distinguished by their lack of a true nucleus and membrane-bound organelles.
  • 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_69a2e80111fc8190961d5b7c6154123f completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2ee8d835881908403ea23901e52b3 completed Feb. 28, 2026, 1:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69a41b4ce1648190b1f46ba33d7cf946 completed March 1, 2026, 10:56 a.m.
NEDg Description generation batch_69a41bc18b388190ae97d97656294e7b completed March 1, 2026, 10:58 a.m.
NED2 Entity disambiguation (via description) batch_69a422983e708190904cd891d3996338 completed March 1, 2026, 11:27 a.m.
Created at: Feb. 28, 2026, 1:09 p.m.