Triple
T7168964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U visa |
E167142
|
entity |
| Predicate | maximumInitialValidity |
P74511
|
FINISHED |
| Object | up to four years, subject to exceptions |
—
|
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: up to four years, subject to exceptions | Statement: [U visa, maximumInitialValidity, up to four years, subject to exceptions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maximumInitialValidity Context triple: [U visa, maximumInitialValidity, up to four years, subject to exceptions]
-
A.
validityType
Indicates the specific kind or category of validity that characterizes how or under what conditions something is considered valid.
-
B.
initialAuthorizedStrength
Indicates the originally approved or designated level, size, or capacity of a force, group, or resource at the time it was first authorized.
-
C.
maximumService
Indicates that an entity provides the highest allowable or achievable level of service within a given context or system.
-
D.
maximumTermCount
Indicates the highest number of terms that are allowed or considered within a given context or operation.
-
E.
maximumDraft
Indicates that there is an upper limit on the number of drafts that can be created, stored, or associated with a given entity or process.
- F. None of above. chosen
Provenance (4 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_69c68888c10c819095e0383020225758 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e85c606081909f76d76fc5b90bc8 |
completed | March 27, 2026, 8:28 p.m. |
| PD | Predicate disambiguation | batch_69c6e1ce5f048190808c378a980f7bb6 |
completed | March 27, 2026, 8 p.m. |
| PDg | Predicate description generation | batch_69c6e24af9ac8190b24eee206ba8be36 |
completed | March 27, 2026, 8:02 p.m. |
Created at: March 27, 2026, 2:48 p.m.