Triple
T7232018
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Office of Biometric Identity Management |
E154924
|
entity |
| Predicate | operates |
P24
|
FINISHED |
| Object |
Automated Biometric Identification System
The Automated Biometric Identification System is a large-scale U.S. government database and matching system that stores and analyzes biometric data, such as fingerprints and facial images, to verify and identify individuals for security and immigration purposes.
|
E650441
|
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: Automated Biometric Identification System | Statement: [Office of Biometric Identity Management, operates, Automated Biometric Identification System]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Automated Biometric Identification System Context triple: [Office of Biometric Identity Management, operates, Automated Biometric Identification System]
-
A.
Integrated Automated Fingerprint Identification System
The Integrated Automated Fingerprint Identification System is the FBI’s large-scale computerized system for storing, searching, and matching fingerprint and biometric data to support criminal identification and investigative work.
-
B.
Real-Time Automated Personnel Identification System
The Real-Time Automated Personnel Identification System (RAPIDS) is a U.S. Department of Defense system used to verify identity and issue Common Access Cards and other identification credentials to eligible personnel and dependents.
-
C.
Automated Passport Control kiosks
Automated Passport Control kiosks are self-service machines at U.S. ports of entry that streamline and expedite the inspection process for eligible travelers by automating passport and customs data collection.
-
D.
Latent and Palm Print Services
Latent and Palm Print Services is a component of the FBI’s Next Generation Identification system that manages, stores, and analyzes latent and palm print data to support biometric identification and criminal investigations.
-
E.
Combined DNA Index System
The Combined DNA Index System (CODIS) is a national DNA database in the United States that enables law enforcement agencies to store, compare, and match DNA profiles for criminal investigations and identification.
- 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: Automated Biometric Identification System Triple: [Office of Biometric Identity Management, operates, Automated Biometric Identification System]
Generated description
The Automated Biometric Identification System is a large-scale U.S. government database and matching system that stores and analyzes biometric data, such as fingerprints and facial images, to verify and identify individuals for security and immigration purposes.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Automated Biometric Identification System Target entity description: The Automated Biometric Identification System is a large-scale U.S. government database and matching system that stores and analyzes biometric data, such as fingerprints and facial images, to verify and identify individuals for security and immigration purposes.
-
A.
Integrated Automated Fingerprint Identification System
The Integrated Automated Fingerprint Identification System is the FBI’s large-scale computerized system for storing, searching, and matching fingerprint and biometric data to support criminal identification and investigative work.
-
B.
Real-Time Automated Personnel Identification System
The Real-Time Automated Personnel Identification System (RAPIDS) is a U.S. Department of Defense system used to verify identity and issue Common Access Cards and other identification credentials to eligible personnel and dependents.
-
C.
Automated Passport Control kiosks
Automated Passport Control kiosks are self-service machines at U.S. ports of entry that streamline and expedite the inspection process for eligible travelers by automating passport and customs data collection.
-
D.
Latent and Palm Print Services
Latent and Palm Print Services is a component of the FBI’s Next Generation Identification system that manages, stores, and analyzes latent and palm print data to support biometric identification and criminal investigations.
-
E.
Combined DNA Index System
The Combined DNA Index System (CODIS) is a national DNA database in the United States that enables law enforcement agencies to store, compare, and match DNA profiles for criminal investigations and identification.
- 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_69c68811dd1c8190ac460bb39e64e1f0 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea106cc881909348be576ced4beb |
completed | March 27, 2026, 8:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7cc2786f88190b0008891f801ca95 |
completed | March 28, 2026, 12:40 p.m. |
| NEDg | Description generation | batch_69c7cd7cb5f081908c2ca7ce8653f25f |
completed | March 28, 2026, 12:45 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7cdf9e0608190a466ed638b728924 |
completed | March 28, 2026, 12:47 p.m. |
Created at: March 27, 2026, 2:54 p.m.