Triple

T315330
Position Surface form Disambiguated ID Type / Status
Subject Cancer Research UK Cambridge Institute E7692 entity
Predicate collaboratesWith P37 FINISHED
Object Cambridge Stem Cell Institute
The Cambridge Stem Cell Institute is a leading research center at the University of Cambridge dedicated to understanding stem cell biology and translating this knowledge into new treatments for human disease.
E44280 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: Cambridge Stem Cell Institute | Statement: [Cancer Research UK Cambridge Institute, collaboratesWith, Cambridge Stem Cell Institute]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cambridge Stem Cell Institute
Context triple: [Cancer Research UK Cambridge Institute, collaboratesWith, Cambridge Stem Cell Institute]
  • A. Babraham Research Campus
    Babraham Research Campus is a major life sciences research and innovation hub near Cambridge, England, focused on bioscience, biotechnology, and academic–industry collaboration.
  • B. CRUK Cambridge Institute
    CRUK Cambridge Institute is a leading cancer research center at the University of Cambridge that integrates laboratory science with clinical and computational approaches to improve cancer diagnosis, treatment, and prevention.
  • C. Cambridge Biomedical Campus
    Cambridge Biomedical Campus is a major medical and life sciences hub in Cambridge, England, integrating leading hospitals, research institutes, and biotechnology companies.
  • D. Wellcome–MRC Institute of Metabolic Science
    The Wellcome–MRC Institute of Metabolic Science is a leading research center at the University of Cambridge focused on understanding and treating metabolic diseases such as obesity and diabetes.
  • E. Broad Institute of MIT and Harvard
    The Broad Institute of MIT and Harvard is a leading biomedical and genomic research center known for large-scale collaborative projects that advance understanding of human disease and inform new therapies.
  • 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: Cambridge Stem Cell Institute
Triple: [Cancer Research UK Cambridge Institute, collaboratesWith, Cambridge Stem Cell Institute]
Generated description
The Cambridge Stem Cell Institute is a leading research center at the University of Cambridge dedicated to understanding stem cell biology and translating this knowledge into new treatments for human disease.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cambridge Stem Cell Institute
Target entity description: The Cambridge Stem Cell Institute is a leading research center at the University of Cambridge dedicated to understanding stem cell biology and translating this knowledge into new treatments for human disease.
  • A. Babraham Research Campus
    Babraham Research Campus is a major life sciences research and innovation hub near Cambridge, England, focused on bioscience, biotechnology, and academic–industry collaboration.
  • B. CRUK Cambridge Institute
    CRUK Cambridge Institute is a leading cancer research center at the University of Cambridge that integrates laboratory science with clinical and computational approaches to improve cancer diagnosis, treatment, and prevention.
  • C. Cambridge Biomedical Campus
    Cambridge Biomedical Campus is a major medical and life sciences hub in Cambridge, England, integrating leading hospitals, research institutes, and biotechnology companies.
  • D. Wellcome–MRC Institute of Metabolic Science
    The Wellcome–MRC Institute of Metabolic Science is a leading research center at the University of Cambridge focused on understanding and treating metabolic diseases such as obesity and diabetes.
  • E. Broad Institute of MIT and Harvard
    The Broad Institute of MIT and Harvard is a leading biomedical and genomic research center known for large-scale collaborative projects that advance understanding of human disease and inform new therapies.
  • 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_69a2e7e7af7881908890039d6be4e9b8 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ea6462148190825acc57f6d2adaf completed Feb. 28, 2026, 1:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3d7e3015081908f494ff2a6df5c86 completed March 1, 2026, 6:08 a.m.
NEDg Description generation batch_69a3d8b2d6748190ace042f42af16595 completed March 1, 2026, 6:12 a.m.
NED2 Entity disambiguation (via description) batch_69a3d9665610819084739d23f3a14816 completed March 1, 2026, 6:15 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.