Triple
T300404
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HL7 standards |
E6183
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object |
LOINC
LOINC (Logical Observation Identifiers Names and Codes) is a widely used international standard for identifying laboratory tests, clinical measurements, and other health observations in electronic health records and data exchange.
|
E39023
|
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: LOINC | Statement: [HL7 standards, relatedTo, LOINC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LOINC Context triple: [HL7 standards, relatedTo, LOINC]
-
A.
SNOMED CT
SNOMED CT is a comprehensive, multilingual clinical healthcare terminology used worldwide to standardize the recording and sharing of medical information in electronic health records.
-
B.
International Classification of Diseases
The International Classification of Diseases is a globally used diagnostic system that standardizes codes for diseases, health conditions, and related medical problems to support clinical care, research, and health statistics.
-
C.
ICD-O
ICD-O (International Classification of Diseases for Oncology) is a specialized coding system used worldwide for classifying tumors by site, morphology, behavior, and grade in cancer registration and research.
-
D.
HL7 standards
HL7 standards are a widely adopted set of international specifications for the exchange, integration, sharing, and retrieval of electronic health information between healthcare systems.
-
E.
International Classification of Health Interventions
The International Classification of Health Interventions is a standardized global system developed by the World Health Organization to categorize and code medical and health-related procedures and interventions for use in clinical practice, research, and health statistics.
- 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: LOINC Triple: [HL7 standards, relatedTo, LOINC]
Generated description
LOINC (Logical Observation Identifiers Names and Codes) is a widely used international standard for identifying laboratory tests, clinical measurements, and other health observations in electronic health records and data exchange.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: LOINC Target entity description: LOINC (Logical Observation Identifiers Names and Codes) is a widely used international standard for identifying laboratory tests, clinical measurements, and other health observations in electronic health records and data exchange.
-
A.
SNOMED CT
SNOMED CT is a comprehensive, multilingual clinical healthcare terminology used worldwide to standardize the recording and sharing of medical information in electronic health records.
-
B.
International Classification of Diseases
The International Classification of Diseases is a globally used diagnostic system that standardizes codes for diseases, health conditions, and related medical problems to support clinical care, research, and health statistics.
-
C.
ICD-O
ICD-O (International Classification of Diseases for Oncology) is a specialized coding system used worldwide for classifying tumors by site, morphology, behavior, and grade in cancer registration and research.
-
D.
HL7 standards
HL7 standards are a widely adopted set of international specifications for the exchange, integration, sharing, and retrieval of electronic health information between healthcare systems.
-
E.
International Classification of Health Interventions
The International Classification of Health Interventions is a standardized global system developed by the World Health Organization to categorize and code medical and health-related procedures and interventions for use in clinical practice, research, and health statistics.
- 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_69a2e79114b081909490b3bf5a5dbb51 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2e9e6a8308190b9bd15310e324504 |
completed | Feb. 28, 2026, 1:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3b0732b5c81908f08a37ce720bc04 |
completed | March 1, 2026, 3:20 a.m. |
| NEDg | Description generation | batch_69a3b0e4a5b4819095d579ef1a23ee07 |
completed | March 1, 2026, 3:22 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a3b151a98c81909fcd775afcbebfe1 |
completed | March 1, 2026, 3:24 a.m. |
Created at: Feb. 28, 2026, 1:06 p.m.