Triple

T21289788
Position Surface form Disambiguated ID Type / Status
Subject Paul Schimmel E524754 entity
Predicate coFounded P104 FINISHED
Object Repligen
Repligen is a biotechnology company known for developing and supplying bioprocessing technologies and materials used in the manufacture of biologic drugs.
 E1476314 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: Repligen | Statement: [Paul Schimmel, coFounded, Repligen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Repligen
Context triple: [Paul Schimmel, coFounded, Repligen]
  • A. Hargreave-Rasch Biotechnologies
    Hargreave-Rasch Biotechnologies is a fictional advanced biotech corporation in the Crysis video game universe, known for its cutting-edge research into alien technology and military applications.
  • B. Lonza
    Lonza is a global Swiss-based life sciences company specializing in pharmaceutical, biotech, and nutrition products and services, particularly in contract development and manufacturing.
  • C. Lonza
    Lonza is a river in the Swiss canton of Valais that flows through the Lötschental valley before joining the Rhône.
  • D. Horizon Discovery
    Horizon Discovery is a biotechnology company specializing in gene editing and cell-based research tools used for drug discovery and development.
  • E. Insitro
    Insitro is a biotechnology company that uses machine learning and high-throughput biology to accelerate drug discovery and development.
  • 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: Repligen
Triple: [Paul Schimmel, coFounded, Repligen]
Generated description
Repligen is a biotechnology company known for developing and supplying bioprocessing technologies and materials used in the manufacture of biologic drugs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Repligen
Target entity description: Repligen is a biotechnology company known for developing and supplying bioprocessing technologies and materials used in the manufacture of biologic drugs.
  • A. Hargreave-Rasch Biotechnologies
    Hargreave-Rasch Biotechnologies is a fictional advanced biotech corporation in the Crysis video game universe, known for its cutting-edge research into alien technology and military applications.
  • B. Lonza
    Lonza is a global Swiss-based life sciences company specializing in pharmaceutical, biotech, and nutrition products and services, particularly in contract development and manufacturing.
  • C. Lonza
    Lonza is a river in the Swiss canton of Valais that flows through the Lötschental valley before joining the Rhône.
  • D. Horizon Discovery
    Horizon Discovery is a biotechnology company specializing in gene editing and cell-based research tools used for drug discovery and development.
  • E. Insitro
    Insitro is a biotechnology company that uses machine learning and high-throughput biology to accelerate drug discovery and development.
  • 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_69e0b5171f6c8190a5d57201ede73811 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e736d9467881908ec5b1dec76e6f5d completed April 21, 2026, 8:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09980c3fbc8190aefe065a0d6cd8b5 completed May 17, 2026, 10:27 a.m.
NEDg Description generation batch_6a0998a3326481908a4dfddfb7b2ecd9 completed May 17, 2026, 10:29 a.m.
NED2 Entity disambiguation (via description) batch_6a09996c8d7c81908cc9874f6e1a3fff completed May 17, 2026, 10:33 a.m.
Created at: April 16, 2026, 4:03 p.m.