Triple

T19772999
Position Surface form Disambiguated ID Type / Status
Subject Prevnar 13 E474933 entity
Predicate isConjugatedTo P137279 FINISHED
Object CRM197 diphtheria protein
CRM197 diphtheria protein is a non-toxic mutant form of diphtheria toxin widely used as a carrier protein in conjugate vaccines to enhance immune responses to attached polysaccharide antigens.
E1394317 NE FINISHED

How this triple was built (5 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: CRM197 diphtheria protein | Statement: [Prevnar 13, isConjugatedTo, CRM197 diphtheria protein]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CRM197 diphtheria protein
Context triple: [Prevnar 13, isConjugatedTo, CRM197 diphtheria protein]
  • A. Corynebacterium diphtheriae
    Corynebacterium diphtheriae is a Gram-positive, toxin-producing bacterium that causes the infectious disease diphtheria in humans.
  • B. diphtheria antitoxin
    Diphtheria antitoxin is a serum-based immune therapy that neutralizes the toxin produced by Corynebacterium diphtheriae, used to treat and prevent the severe complications of diphtheria infection.
  • C. diphtheria
    Diphtheria is a serious, potentially life-threatening infectious disease caused by Corynebacterium diphtheriae, characterized by sore throat, fever, and a thick gray membrane in the throat that can obstruct breathing.
  • D. Streptomyces phage phiC31
    Streptomyces phage phiC31 is a bacteriophage whose site-specific integrase has become a widely used tool for stable genome engineering in bacteria, plants, and animals.
  • E. Serpins
    Serpins is a civil parish in the municipality of Lousã in central Portugal, known for its natural landscapes and proximity to the Serra da Lousã.
  • 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: CRM197 diphtheria protein
Triple: [Prevnar 13, isConjugatedTo, CRM197 diphtheria protein]
Generated description
CRM197 diphtheria protein is a non-toxic mutant form of diphtheria toxin widely used as a carrier protein in conjugate vaccines to enhance immune responses to attached polysaccharide antigens.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: CRM197 diphtheria protein
Target entity description: CRM197 diphtheria protein is a non-toxic mutant form of diphtheria toxin widely used as a carrier protein in conjugate vaccines to enhance immune responses to attached polysaccharide antigens.
  • A. Corynebacterium diphtheriae
    Corynebacterium diphtheriae is a Gram-positive, toxin-producing bacterium that causes the infectious disease diphtheria in humans.
  • B. diphtheria antitoxin
    Diphtheria antitoxin is a serum-based immune therapy that neutralizes the toxin produced by Corynebacterium diphtheriae, used to treat and prevent the severe complications of diphtheria infection.
  • C. diphtheria
    Diphtheria is a serious, potentially life-threatening infectious disease caused by Corynebacterium diphtheriae, characterized by sore throat, fever, and a thick gray membrane in the throat that can obstruct breathing.
  • D. Streptomyces phage phiC31
    Streptomyces phage phiC31 is a bacteriophage whose site-specific integrase has become a widely used tool for stable genome engineering in bacteria, plants, and animals.
  • E. Serpins
    Serpins is a civil parish in the municipality of Lousã in central Portugal, known for its natural landscapes and proximity to the Serra da Lousã.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isConjugatedTo
Context triple: [Prevnar 13, isConjugatedTo, CRM197 diphtheria protein]
  • A. conjugate
    Indicates that one entity is a grammatical or mathematical counterpart of another, linked by a specific transformation such as verb inflection or complex-number pairing.
  • B. conjugateTo
    Indicates that one entity can be transformed into the other by a specific equivalence operation (such as similarity or group conjugation), so they are equivalent up to that transformation.
  • C. hasConjunctForms
    Indicates that an entity is associated with one or more conjunct (combined or compound) forms of itself or related elements.
  • D. isContractionOf
    Indicates that one term is a shortened or combined form derived from another, more complete expression.
  • E. hasConjugationOperation
    Indicates that there exists an operation that transforms an entity into its conjugate form (e.g., algebraic, complex, or grammatical conjugation).
  • F. None of above. chosen

Provenance (7 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_69d8e51a43a08190956bc6df13c91a77 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6535e450c8190a2628245ae0d0bd3 completed April 20, 2026, 4:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07bd76afe08190b958bd49acf21c4a completed May 16, 2026, 12:42 a.m.
NEDg Description generation batch_6a07be5426c48190bb7b0fc315fa2f6a completed May 16, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_6a07bf9682fc8190a33ea75dba8d88d6 completed May 16, 2026, 12:51 a.m.
PD Predicate disambiguation batch_69e53053ed2881908400becdfada7fd3 completed April 19, 2026, 7:43 p.m.
PDg Predicate description generation batch_69e532bbedf081908d801600e2af94a7 completed April 19, 2026, 7:53 p.m.
Created at: April 10, 2026, 1:48 p.m.