Triple

T19401411
Position Surface form Disambiguated ID Type / Status
Subject SecurID E485333 entity
Predicate hasComponent P35 FINISHED
Object SecurID software token 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: SecurID software token | Statement: [SecurID, hasComponent, SecurID software token]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SecurID software token
Context triple: [SecurID, hasComponent, SecurID software token]
  • A. SecurID chosen
    SecurID is a widely used two-factor authentication system that provides time-based one-time passwords via hardware or software tokens to enhance secure access to systems and data.
  • B. OnePass
    OnePass was Continental Airlines’ frequent flyer loyalty program that allowed passengers to earn and redeem miles for flights and travel rewards.
  • C. Authy
    Authy is a two-factor authentication app and service that provides secure, multi-device token-based login protection for online accounts.
  • D. Gemalto
    Gemalto is a digital security company known for providing smart cards, SIM cards, and secure software solutions for telecommunications, banking, and government identification.
  • E. FIDO U2F
    FIDO U2F is an open authentication standard that enables strong, phishing-resistant two-factor authentication using dedicated hardware security keys.
  • 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.