Triple

T2805384
Position Surface form Disambiguated ID Type / Status
Subject Sébastien Jodogne E54040 entity
Predicate knownFor P22 FINISHED
Object Orthanc
Orthanc is an open-source, lightweight DICOM server and ecosystem designed for medical imaging storage, retrieval, and integration in healthcare and research environments.
 E299654 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: Orthanc | Statement: [Sébastien Jodogne, knownFor, Orthanc]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Orthanc
Context triple: [Sébastien Jodogne, knownFor, Orthanc]
  • A. OpenMRS
    OpenMRS is an open-source medical record system platform widely used in resource-constrained settings to improve healthcare delivery and data management.
  • B. Cloud Healthcare API
    Cloud Healthcare API is a Google Cloud service that enables secure storage, management, and exchange of healthcare data using standard formats like HL7, FHIR, and DICOM.
  • C. DICOM Unique Identifier (UID)
    DICOM Unique Identifier (UID) is a globally unique numeric string used in medical imaging to unambiguously identify objects such as studies, series, images, and other DICOM entities.
  • D. DICOM Application Entity
    A DICOM Application Entity is a networked software or device component in medical imaging systems that sends, receives, and processes DICOM messages and services for exchanging clinical data.
  • E. Flatiron Health
    Flatiron Health is a healthcare technology company that specializes in using real-world oncology data and software to improve cancer care and research.
  • 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: Orthanc
Triple: [Sébastien Jodogne, knownFor, Orthanc]
Generated description
Orthanc is an open-source, lightweight DICOM server and ecosystem designed for medical imaging storage, retrieval, and integration in healthcare and research environments.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Orthanc
Target entity description: Orthanc is an open-source, lightweight DICOM server and ecosystem designed for medical imaging storage, retrieval, and integration in healthcare and research environments.
  • A. OpenMRS
    OpenMRS is an open-source medical record system platform widely used in resource-constrained settings to improve healthcare delivery and data management.
  • B. Cloud Healthcare API
    Cloud Healthcare API is a Google Cloud service that enables secure storage, management, and exchange of healthcare data using standard formats like HL7, FHIR, and DICOM.
  • C. DICOM Unique Identifier (UID)
    DICOM Unique Identifier (UID) is a globally unique numeric string used in medical imaging to unambiguously identify objects such as studies, series, images, and other DICOM entities.
  • D. DICOM Application Entity
    A DICOM Application Entity is a networked software or device component in medical imaging systems that sends, receives, and processes DICOM messages and services for exchanging clinical data.
  • E. Flatiron Health
    Flatiron Health is a healthcare technology company that specializes in using real-world oncology data and software to improve cancer care and research.
  • 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_69ab49dcee188190b5c6eca9ae9e3469 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abde1525888190b3c04e10043c67d6 completed March 7, 2026, 8:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc674217c81908177b088cc824e7b completed March 10, 2026, 7:21 a.m.
NEDg Description generation batch_69afc863133c8190b129a55f8d28966f completed March 10, 2026, 7:29 a.m.
NED2 Entity disambiguation (via description) batch_69afc8d43e608190b33159a464dc2e8c completed March 10, 2026, 7:31 a.m.
Created at: March 6, 2026, 9:59 p.m.