Triple

T19401436
Position Surface form Disambiguated ID Type / Status
Subject RSA Archer E485334 entity
Predicate developer P73 FINISHED
Object RSA Security NE NERFINISHED

How this triple was built (2 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: RSA Security | Statement: [RSA Archer, developer, RSA Security]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RSA Security
Context triple: [RSA Archer, developer, RSA Security]
  • A. RSA Security chosen
    RSA Security is a pioneering American cybersecurity company best known for its contributions to public-key cryptography and secure data encryption technologies.
  • B. RSA
    RSA is a widely used public-key cryptographic algorithm that enables secure key exchange and digital signatures in many internet security protocols.
  • C. RSA
    RSA is the three-letter World Rugby trigram used to represent the South Africa national rugby union team in international competitions and official records.
  • D. RSA Design
    RSA Design is a creative design division of the production company RSA Films, specializing in visual and graphic solutions for film, advertising, and branded content.
  • E. RSA Fellowship
    The RSA Fellowship is a global community of accomplished individuals from diverse fields who collaborate to address social challenges and promote innovative solutions for the public good.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d8e8d5162481909db12435d9535c1a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e62577454c81909d5bcd07e99b27e4 completed April 20, 2026, 1:09 p.m.
Created at: April 10, 2026, 1:36 p.m.