Triple

T37352585
Position Surface form Disambiguated ID Type / Status
Subject K-1 visa E927363 entity
Predicate requiresBiometrics P63130 FINISHED
Object yes, during USCIS or adjustment process LITERAL 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: yes, during USCIS or adjustment process | Statement: [K-1 visa, requiresBiometrics, yes, during USCIS or adjustment process]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: requiresBiometrics
Context triple: [K-1 visa, requiresBiometrics, yes, during USCIS or adjustment process]
  • A. includesBiometrics chosen
    Indicates that one entity contains, uses, or is associated with biometric data or biometric identifiers of another entity.
  • B. hasFingerprintSensor
    Indicates that an entity is equipped with or includes a fingerprint recognition sensor.
  • C. hasFaceUnlock
    Indicates that an entity supports or is equipped with a facial recognition–based unlocking feature.
  • D. requiresPass
    Indicates that access to or participation in something is conditional on possessing a valid pass.
  • E. nonceRequirement
    Indicates that a unique, one-time-use value (nonce) is required to be present or validated as part of the interaction or transaction between entities.
  • F. None of above.

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_69f76eb5e034819088e53ab5b7909a68 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_6a0045a7b4c081908e4dedabda7cf790 completed May 10, 2026, 8:45 a.m.
PD Predicate disambiguation batch_6a0042b148a48190974b173f352e4b7f completed May 10, 2026, 8:32 a.m.
Created at: May 3, 2026, 4:16 p.m.