Triple
T26020898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Form I-918, Petition for U Nonimmigrant Status |
E647149
|
entity |
| Predicate | formLanguage |
P6281
|
FINISHED |
| Object | English |
—
|
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: English | Statement: [Form I-918, Petition for U Nonimmigrant Status, formLanguage, English]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formLanguage Context triple: [Form I-918, Petition for U Nonimmigrant Status, formLanguage, English]
-
A.
languageForm
chosen
Indicates the specific linguistic form or expression in which something is conveyed or represented.
-
B.
titleLanguageForm
Indicates the specific linguistic form or variant in which a title is expressed (e.g., language, script, or transliteration form).
-
C.
formerLanguage
Indicates that one entity was previously the language of another entity but is no longer in that role.
-
D.
languageUse
Indicates the language or languages an entity uses for communication, expression, or interaction.
-
E.
languageSubject
Indicates that a particular language is the subject or topic being studied, discussed, or otherwise focused on in relation to another entity.
- 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_69e77e8aa65881909ca58918f29ab2a0 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f605e5af4081909e3862d44e313d7f |
completed | May 2, 2026, 2:10 p.m. |
| PD | Predicate disambiguation | batch_69f4a10728e08190bc0b96c558740f51 |
completed | May 1, 2026, 12:48 p.m. |
Created at: April 22, 2026, 9:03 a.m.