Triple
T28657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Financial Crimes Enforcement Network |
E570
|
entity |
| Predicate | maintainsSystem |
P636
|
FINISHED |
| Object |
BSA E-Filing System
The BSA E-Filing System is an online platform used by financial institutions and other obligated entities in the United States to electronically submit Bank Secrecy Act reports and related regulatory filings.
|
E2183
|
NE FINISHED |
How this triple was built (5 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: BSA E-Filing System | Statement: [Financial Crimes Enforcement Network, maintainsSystem, BSA E-Filing System]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BSA E-Filing System Context triple: [Financial Crimes Enforcement Network, maintainsSystem, BSA E-Filing System]
-
A.
oN-Line System
The oN-Line System (NLS) was an early, pioneering computer system that introduced many foundational concepts of modern computing, including the mouse, hypertext, and interactive graphical user interfaces.
-
B.
ERP
ERP is the commonly used abbreviation for the Marshall Plan, the U.S.-led post–World War II European Recovery Program that financed and coordinated Western Europe’s economic reconstruction.
-
C.
Tymshare
Tymshare was an influential American time-sharing and computer services company active in the 1960s–1980s that helped pioneer remote computing and software services for businesses.
-
D.
FJCC
FJCC was a major mid-20th-century U.S. computing conference that served as a key forum for presenting influential research and developments in computer science and technology.
-
E.
United States Patent and Trademark Office
The United States Patent and Trademark Office is the federal agency responsible for granting patents, registering trademarks, and overseeing key aspects of intellectual property protection in the United States.
- 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: BSA E-Filing System Triple: [Financial Crimes Enforcement Network, maintainsSystem, BSA E-Filing System]
Generated description
The BSA E-Filing System is an online platform used by financial institutions and other obligated entities in the United States to electronically submit Bank Secrecy Act reports and related regulatory filings.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: BSA E-Filing System Target entity description: The BSA E-Filing System is an online platform used by financial institutions and other obligated entities in the United States to electronically submit Bank Secrecy Act reports and related regulatory filings.
-
A.
oN-Line System
The oN-Line System (NLS) was an early, pioneering computer system that introduced many foundational concepts of modern computing, including the mouse, hypertext, and interactive graphical user interfaces.
-
B.
ERP
ERP is the commonly used abbreviation for the Marshall Plan, the U.S.-led post–World War II European Recovery Program that financed and coordinated Western Europe’s economic reconstruction.
-
C.
Tymshare
Tymshare was an influential American time-sharing and computer services company active in the 1960s–1980s that helped pioneer remote computing and software services for businesses.
-
D.
FJCC
FJCC was a major mid-20th-century U.S. computing conference that served as a key forum for presenting influential research and developments in computer science and technology.
-
E.
United States Patent and Trademark Office
The United States Patent and Trademark Office is the federal agency responsible for granting patents, registering trademarks, and overseeing key aspects of intellectual property protection in the United States.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maintainsSystem Context triple: [Financial Crimes Enforcement Network, maintainsSystem, BSA E-Filing System]
-
A.
partOfSystem
Indicates that one entity functions as a component or subsystem within the structure or organization of another entity.
-
B.
system
Indicates that an entity functions as or belongs to a structured, organized set of components or processes that operate together as a system.
-
C.
maintenance
Indicates that an entity performs, requires, or is involved in upkeep, repair, or preservation activities for another entity or system.
-
D.
notableSystem
Indicates that a system is recognized as significant, prominent, or noteworthy in a particular context or domain.
-
E.
responsibleFor
chosen
Indicates that one entity has a duty, obligation, or role to manage, oversee, or be accountable for another entity or outcome.
- F. None of above.
Provenance (6 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_69a2479dec388190967ba648663442c9 |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a24925607c8190a9ce7ec834f3e5bb |
completed | Feb. 28, 2026, 1:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a24e5d121c8190bf7bb88346dcc141 |
completed | Feb. 28, 2026, 2:09 a.m. |
| NEDg | Description generation | batch_69a24edff52081909ec669158900651c |
completed | Feb. 28, 2026, 2:11 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a24f4a96288190981be6076e919262 |
completed | Feb. 28, 2026, 2:13 a.m. |
| PD | Predicate disambiguation | batch_69a2486bd74c81908d32be3c7d22f51f |
completed | Feb. 28, 2026, 1:44 a.m. |
Created at: Feb. 28, 2026, 1:44 a.m.