Triple

T13425305
Position Surface form Disambiguated ID Type / Status
Subject Twilio E313463 entity
Predicate hasProduct P3585 FINISHED
Object Twilio Authy E485333 NE FINISHED

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: Twilio Authy | Statement: [Twilio, hasProduct, Twilio Authy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Twilio Authy
Context triple: [Twilio, hasProduct, Twilio Authy]
  • A. OTP
    OTP is the acronym commonly used for the Office of the Prosecutor of the International Criminal Court, the body responsible for investigating and prosecuting individuals for international crimes such as genocide, war crimes, and crimes against humanity.
  • B. OTP
    OTP is the abbreviation for the U.S. federal Office of Telecommunications Policy, a former executive office responsible for shaping national telecommunications policy.
  • C. OTP
    OTP (Open Telecom Platform) is a collection of Erlang libraries and design principles for building scalable, fault-tolerant, concurrent systems.
  • D. OTP
    OTP is the three-letter IATA airport code for Henri Coandă International Airport, the main international airport serving Bucharest, Romania.
  • E. 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.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d806ad0c44819088833ae1ec9e9690 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaed066408190a416880affd8416e completed April 12, 2026, 2:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7308673488190a64f4b205899605b completed May 3, 2026, 11:24 a.m.
Created at: April 9, 2026, 9:40 p.m.