Triple
T5890330
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uniform Crime Reporting Program |
E130971
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Law Enforcement Officers Killed and Assaulted Program
The Law Enforcement Officers Killed and Assaulted Program is a U.S. national data collection initiative that compiles and analyzes statistics on officers feloniously or accidentally killed and assaulted in the line of duty.
|
E552326
|
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: Law Enforcement Officers Killed and Assaulted Program | Statement: [Uniform Crime Reporting Program, hasPart, Law Enforcement Officers Killed and Assaulted Program]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Law Enforcement Officers Killed and Assaulted Program Context triple: [Uniform Crime Reporting Program, hasPart, Law Enforcement Officers Killed and Assaulted Program]
-
A.
Law Enforcement Assistance Administration
The Law Enforcement Assistance Administration was a former U.S. federal agency within the Department of Justice that provided funding and support to state and local law enforcement and criminal justice programs in the 1960s–1980s.
-
B.
Office of Justice Programs
The Office of Justice Programs is a component of the U.S. Department of Justice that provides federal leadership, funding, and research support to improve the nation’s criminal and juvenile justice systems and support crime victims.
-
C.
National Institute of Justice
The National Institute of Justice is the research, development, and evaluation agency of the U.S. Department of Justice, focused on advancing scientific knowledge and innovation to improve criminal justice policy and practice.
-
D.
Support Our Law Enforcement and Safe Neighborhoods Act
The Support Our Law Enforcement and Safe Neighborhoods Act, commonly known as Arizona SB 1070, is a controversial 2010 Arizona immigration law that empowered state and local police to enforce federal immigration rules and sparked major legal and political battles over immigration enforcement and civil rights.
-
E.
Committee on Law Enforcement
The Committee on Law Enforcement is a specialized parliamentary body of the Ukrainian Verkhovna Rada responsible for shaping legislation and oversight related to policing, criminal justice, and public security.
- 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: Law Enforcement Officers Killed and Assaulted Program Triple: [Uniform Crime Reporting Program, hasPart, Law Enforcement Officers Killed and Assaulted Program]
Generated description
The Law Enforcement Officers Killed and Assaulted Program is a U.S. national data collection initiative that compiles and analyzes statistics on officers feloniously or accidentally killed and assaulted in the line of duty.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Law Enforcement Officers Killed and Assaulted Program Target entity description: The Law Enforcement Officers Killed and Assaulted Program is a U.S. national data collection initiative that compiles and analyzes statistics on officers feloniously or accidentally killed and assaulted in the line of duty.
-
A.
Law Enforcement Assistance Administration
The Law Enforcement Assistance Administration was a former U.S. federal agency within the Department of Justice that provided funding and support to state and local law enforcement and criminal justice programs in the 1960s–1980s.
-
B.
Office of Justice Programs
The Office of Justice Programs is a component of the U.S. Department of Justice that provides federal leadership, funding, and research support to improve the nation’s criminal and juvenile justice systems and support crime victims.
-
C.
National Institute of Justice
The National Institute of Justice is the research, development, and evaluation agency of the U.S. Department of Justice, focused on advancing scientific knowledge and innovation to improve criminal justice policy and practice.
-
D.
Support Our Law Enforcement and Safe Neighborhoods Act
The Support Our Law Enforcement and Safe Neighborhoods Act, commonly known as Arizona SB 1070, is a controversial 2010 Arizona immigration law that empowered state and local police to enforce federal immigration rules and sparked major legal and political battles over immigration enforcement and civil rights.
-
E.
Committee on Law Enforcement
The Committee on Law Enforcement is a specialized parliamentary body of the Ukrainian Verkhovna Rada responsible for shaping legislation and oversight related to policing, criminal justice, and public security.
- 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_69c0085628dc8190b334c1b44c067efc |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c036b228508190b050acf51860a5c2 |
completed | March 22, 2026, 6:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0b146ad348190baeeecb65f2bf811 |
completed | March 23, 2026, 3:19 a.m. |
| NEDg | Description generation | batch_69c0b2178dc48190948397b948dd1970 |
completed | March 23, 2026, 3:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c0b29d6048819086c4d4cd01c64a51 |
completed | March 23, 2026, 3:25 a.m. |
Created at: March 22, 2026, 3:58 p.m.