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.