Triple

T19142445
Position Surface form Disambiguated ID Type / Status
Subject AR 600-20 E468591 entity
Predicate regulates P46 FINISHED
Object Sexual Harassment/Assault Response and Prevention program
The Sexual Harassment/Assault Response and Prevention (SHARP) program is the U.S. Army’s comprehensive initiative to prevent, respond to, and eliminate sexual harassment and sexual assault within its ranks through training, reporting mechanisms, and victim support services.
E1360576 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: Sexual Harassment/Assault Response and Prevention program | Statement: [AR 600-20, regulates, Sexual Harassment/Assault Response and Prevention program]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sexual Harassment/Assault Response and Prevention program
Context triple: [AR 600-20, regulates, Sexual Harassment/Assault Response and Prevention program]
  • A. Sexual Assault Unit
    The Sexual Assault Unit is a specialized division of the Metropolitan Police Department of the District of Columbia dedicated to investigating and responding to sexual assault crimes and supporting survivors.
  • B. Family Violence Prevention and Services Program
    The Family Violence Prevention and Services Program is a U.S. federal initiative that funds and supports shelters, services, and prevention efforts for survivors of domestic and family violence.
  • C. Empowerment of Women Programme
    The Empowerment of Women Programme is an initiative of the North-South Centre of the Council of Europe that promotes gender equality and strengthens women’s participation in democratic and social life across regions.
  • D. Protection and Advocacy Systems program
    The Protection and Advocacy Systems program is a nationwide network of federally mandated organizations that protect and advance the rights of people with disabilities through legal advocacy, investigation, and representation.
  • E. Women and the Law Program
    Women and the Law Program is a specialized academic and advocacy center at Washington College of Law focused on advancing gender equality and women’s rights through legal education, research, and policy work.
  • 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: Sexual Harassment/Assault Response and Prevention program
Triple: [AR 600-20, regulates, Sexual Harassment/Assault Response and Prevention program]
Generated description
The Sexual Harassment/Assault Response and Prevention (SHARP) program is the U.S. Army’s comprehensive initiative to prevent, respond to, and eliminate sexual harassment and sexual assault within its ranks through training, reporting mechanisms, and victim support services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sexual Harassment/Assault Response and Prevention program
Target entity description: The Sexual Harassment/Assault Response and Prevention (SHARP) program is the U.S. Army’s comprehensive initiative to prevent, respond to, and eliminate sexual harassment and sexual assault within its ranks through training, reporting mechanisms, and victim support services.
  • A. Sexual Assault Unit
    The Sexual Assault Unit is a specialized division of the Metropolitan Police Department of the District of Columbia dedicated to investigating and responding to sexual assault crimes and supporting survivors.
  • B. Family Violence Prevention and Services Program
    The Family Violence Prevention and Services Program is a U.S. federal initiative that funds and supports shelters, services, and prevention efforts for survivors of domestic and family violence.
  • C. Empowerment of Women Programme
    The Empowerment of Women Programme is an initiative of the North-South Centre of the Council of Europe that promotes gender equality and strengthens women’s participation in democratic and social life across regions.
  • D. Protection and Advocacy Systems program
    The Protection and Advocacy Systems program is a nationwide network of federally mandated organizations that protect and advance the rights of people with disabilities through legal advocacy, investigation, and representation.
  • E. Women and the Law Program
    Women and the Law Program is a specialized academic and advocacy center at Washington College of Law focused on advancing gender equality and women’s rights through legal education, research, and policy work.
  • 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_69d8dd0796a48190b34ce4cd9d3f3be5 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e976e340819098efccc30b2eef0e completed April 20, 2026, 8:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a06f24c1da0819083178d4d49f4bfe4 completed May 15, 2026, 10:15 a.m.
NEDg Description generation batch_6a06f34a4f1c8190b08e2ecddcdf2c27 completed May 15, 2026, 10:19 a.m.
NED2 Entity disambiguation (via description) batch_6a06f3d5b3408190b5fe843039dd8a74 completed May 15, 2026, 10:22 a.m.
Created at: April 10, 2026, 12:05 p.m.