Triple

T13320091
Position Surface form Disambiguated ID Type / Status
Subject AMD Instinct E317291 entity
Predicate architectureFamily P8152 FINISHED
Object CDNA
CDNA is AMD’s GPU architecture family optimized for high-performance computing and data center workloads, emphasizing compute efficiency over traditional graphics features.
 E1033638 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: CDNA | Statement: [AMD Instinct, architectureFamily, CDNA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CDNA
Context triple: [AMD Instinct, architectureFamily, CDNA]
  • A. DNAA
    DNAA is the ICAO airport code for Nnamdi Azikiwe International Airport, the main international gateway serving Abuja, Nigeria’s capital city.
  • B. ADN
    ADN is a European treaty that sets safety and environmental regulations for transporting dangerous goods on inland waterways.
  • C. DNA
    DNA is the unicameral legislative body and main law-making institution of the Republic of Suriname.
  • D. DNA
    DNA is a major social-democratic political party in Norway, historically one of the country’s dominant governing parties.
  • E. DNA
    DNA (deoxyribonucleic acid) is the hereditary molecule in almost all living organisms, encoding genetic instructions that guide development, function, and reproduction.
  • 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: CDNA
Triple: [AMD Instinct, architectureFamily, CDNA]
Generated description
CDNA is AMD’s GPU architecture family optimized for high-performance computing and data center workloads, emphasizing compute efficiency over traditional graphics features.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CDNA
Target entity description: CDNA is AMD’s GPU architecture family optimized for high-performance computing and data center workloads, emphasizing compute efficiency over traditional graphics features.
  • A. DNAA
    DNAA is the ICAO airport code for Nnamdi Azikiwe International Airport, the main international gateway serving Abuja, Nigeria’s capital city.
  • B. ADN
    ADN is a European treaty that sets safety and environmental regulations for transporting dangerous goods on inland waterways.
  • C. DNA
    DNA is the unicameral legislative body and main law-making institution of the Republic of Suriname.
  • D. DNA
    DNA is a major social-democratic political party in Norway, historically one of the country’s dominant governing parties.
  • E. DNA
    DNA (deoxyribonucleic acid) is the hereditary molecule in almost all living organisms, encoding genetic instructions that guide development, function, and reproduction.
  • 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_69d806b4d62c81908d4ced1665414be5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d990faa95481908a7fd297959c062e completed April 11, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69f716ee695c81909ffeeb0901ee66c1 completed May 3, 2026, 9:35 a.m.
NEDg Description generation batch_69f717f4d80c8190a1a95c0f2c83c563 completed May 3, 2026, 9:40 a.m.
NED2 Entity disambiguation (via description) batch_69f718b852808190a2a0fb48424bffb0 completed May 3, 2026, 9:43 a.m.
Created at: April 9, 2026, 9:29 p.m.