Triple
T9134641
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USPS Address Management System |
E219170
|
entity |
| Predicate | relatedStandard |
P37
|
FINISHED |
| Object |
Coding Accuracy Support System
The Coding Accuracy Support System (CASS) is a USPS certification program that evaluates and improves the accuracy of address-matching and ZIP Code assignment software used by mailers and service providers.
|
E780562
|
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: Coding Accuracy Support System | Statement: [USPS Address Management System, relatedStandard, Coding Accuracy Support System]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Coding Accuracy Support System Context triple: [USPS Address Management System, relatedStandard, Coding Accuracy Support System]
-
A.
CDSS
CDSS is the state agency in California responsible for overseeing social services programs such as welfare, child welfare, and community care licensing.
-
B.
Fast Healthcare Interoperability Resources
Fast Healthcare Interoperability Resources (FHIR) is a modern, web-based standard for exchanging electronic healthcare information between systems in a consistent and interoperable way.
-
C.
Jameel Clinic for Machine Learning in Health
The Jameel Clinic for Machine Learning in Health is an MIT research center focused on applying artificial intelligence and machine learning to transform disease prevention, diagnosis, and treatment.
-
D.
Regenstrief Medical Record System
The Regenstrief Medical Record System is an early, pioneering electronic medical record platform that helped shape modern health informatics and clinical data management practices.
-
E.
Clinical Document Architecture
Clinical Document Architecture is an HL7 standard that defines the structure and semantics of electronic clinical documents to enable consistent exchange and interoperability in healthcare.
- 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: Coding Accuracy Support System Triple: [USPS Address Management System, relatedStandard, Coding Accuracy Support System]
Generated description
The Coding Accuracy Support System (CASS) is a USPS certification program that evaluates and improves the accuracy of address-matching and ZIP Code assignment software used by mailers and service providers.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Coding Accuracy Support System Target entity description: The Coding Accuracy Support System (CASS) is a USPS certification program that evaluates and improves the accuracy of address-matching and ZIP Code assignment software used by mailers and service providers.
-
A.
CDSS
CDSS is the state agency in California responsible for overseeing social services programs such as welfare, child welfare, and community care licensing.
-
B.
Fast Healthcare Interoperability Resources
Fast Healthcare Interoperability Resources (FHIR) is a modern, web-based standard for exchanging electronic healthcare information between systems in a consistent and interoperable way.
-
C.
Jameel Clinic for Machine Learning in Health
The Jameel Clinic for Machine Learning in Health is an MIT research center focused on applying artificial intelligence and machine learning to transform disease prevention, diagnosis, and treatment.
-
D.
Regenstrief Medical Record System
The Regenstrief Medical Record System is an early, pioneering electronic medical record platform that helped shape modern health informatics and clinical data management practices.
-
E.
Clinical Document Architecture
Clinical Document Architecture is an HL7 standard that defines the structure and semantics of electronic clinical documents to enable consistent exchange and interoperability in healthcare.
- 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_69ca83debfc0819095800583e97ab10f |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8de0dec8190978c80b9ec8bf25c |
completed | April 1, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d047efc5e48190bc8c4a7e865faef9 |
completed | April 3, 2026, 11:06 p.m. |
| NEDg | Description generation | batch_69d04935d4e88190acb4d65a2dc2bc8a |
completed | April 3, 2026, 11:11 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d049e6c4cc81909e08b5aaed9a88dc |
completed | April 3, 2026, 11:14 p.m. |
Created at: March 30, 2026, 7:18 p.m.