Triple
T19309816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Poindexter |
E482933
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Total Information Awareness program |
—
|
NE NERFINISHED |
How this triple was built (3 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: Total Information Awareness program | Statement: [John Poindexter, notableWork, Total Information Awareness program]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Total Information Awareness program Context triple: [John Poindexter, notableWork, Total Information Awareness program]
-
A.
Terrorist Surveillance Program
The Terrorist Surveillance Program was a post-9/11 U.S. National Security Agency warrantless wiretapping initiative that monitored international communications involving suspected terrorists.
-
B.
U.S. Army information assurance program
The U.S. Army information assurance program is the overarching framework that governs how the Army protects, monitors, and secures its information systems and networks against cyber threats.
-
C.
National Intelligence Program
The National Intelligence Program is the U.S. federal budget framework that funds and coordinates the activities of civilian and military intelligence agencies to support national security decision-making.
-
D.
Controlled Unclassified Information program
The Controlled Unclassified Information program is a U.S. federal initiative that standardizes how sensitive but unclassified information is marked, handled, and protected across government agencies and their partners.
-
E.
PRISM surveillance program
The PRISM surveillance program is a classified U.S. National Security Agency data-collection initiative that gathers and analyzes digital communications from major internet companies for intelligence purposes.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Total Information Awareness program Target entity description: The Total Information Awareness program was a controversial early-2000s U.S. Defense Department initiative aimed at using large-scale data mining and surveillance to detect and prevent terrorist activities.
-
A.
Terrorist Surveillance Program
The Terrorist Surveillance Program was a post-9/11 U.S. National Security Agency warrantless wiretapping initiative that monitored international communications involving suspected terrorists.
-
B.
U.S. Army information assurance program
The U.S. Army information assurance program is the overarching framework that governs how the Army protects, monitors, and secures its information systems and networks against cyber threats.
-
C.
National Intelligence Program
The National Intelligence Program is the U.S. federal budget framework that funds and coordinates the activities of civilian and military intelligence agencies to support national security decision-making.
-
D.
Controlled Unclassified Information program
The Controlled Unclassified Information program is a U.S. federal initiative that standardizes how sensitive but unclassified information is marked, handled, and protected across government agencies and their partners.
-
E.
PRISM surveillance program
The PRISM surveillance program is a classified U.S. National Security Agency data-collection initiative that gathers and analyzes digital communications from major internet companies for intelligence purposes.
- F. None of above. chosen
Provenance (2 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_69d8e8d04d5c8190baa816986f2b1d1e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e604cc62e08190b5ba5dfc44efdc5c |
completed | April 20, 2026, 10:49 a.m. |
Created at: April 10, 2026, 1:32 p.m.