Triple

T15523765
Position Surface form Disambiguated ID Type / Status
Subject Special Source Operations E369031 entity
Predicate hasProgram P178 FINISHED
Object OAKSTAR
OAKSTAR is a classified U.S. National Security Agency surveillance program focused on collecting foreign communications data from fiber-optic cables and other high-capacity network infrastructure.
E1161801 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: OAKSTAR | Statement: [Special Source Operations, hasProgram, OAKSTAR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OAKSTAR
Context triple: [Special Source Operations, hasProgram, OAKSTAR]
  • A. OAKN
    OAKN is the ICAO airport code for Kandahar International Airport in Kandahar, Afghanistan.
  • B. OAK
    OAK is the standard three-letter abbreviation used for the Major League Baseball team the Oakland Athletics.
  • C. OAK
    OAK is the standard abbreviation used for the former professional basketball team the Oakland Oaks.
  • D. OAK
    OAK is the IATA airport code for Oakland International Airport, a major commercial airport serving the San Francisco Bay Area in California.
  • E. OAKB
    OAKB is the ICAO airport code for Hamid Karzai International Airport, the main international airport serving Kabul, Afghanistan.
  • 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: OAKSTAR
Triple: [Special Source Operations, hasProgram, OAKSTAR]
Generated description
OAKSTAR is a classified U.S. National Security Agency surveillance program focused on collecting foreign communications data from fiber-optic cables and other high-capacity network infrastructure.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: OAKSTAR
Target entity description: OAKSTAR is a classified U.S. National Security Agency surveillance program focused on collecting foreign communications data from fiber-optic cables and other high-capacity network infrastructure.
  • A. OAKN
    OAKN is the ICAO airport code for Kandahar International Airport in Kandahar, Afghanistan.
  • B. OAK
    OAK is the standard three-letter abbreviation used for the Major League Baseball team the Oakland Athletics.
  • C. OAK
    OAK is the IATA airport code for Oakland International Airport, a major commercial airport serving the San Francisco Bay Area in California.
  • D. OAK
    OAK is the standard abbreviation used for the former professional basketball team the Oakland Oaks.
  • E. OAKB
    OAKB is the ICAO airport code for Hamid Karzai International Airport, the main international airport serving Kabul, Afghanistan.
  • 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_69d85a1794cc8190b0b428716296e63e completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e04143bda08190a2dee44918c1ad1c completed April 16, 2026, 1:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff3d5706948190a1c0f466f7ef8857 completed May 9, 2026, 1:57 p.m.
NEDg Description generation batch_69ff3e5643088190a9b001ef815ddd3a completed May 9, 2026, 2:01 p.m.
NED2 Entity disambiguation (via description) batch_69ff3f4456f88190b7fc9b853b0155e4 completed May 9, 2026, 2:05 p.m.
Created at: April 10, 2026, 4:05 a.m.