Triple
T7231843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Form I-9 |
E154920
|
entity |
| Predicate | listAPurpose |
P75912
|
FINISHED |
| Object | establish both identity and employment authorization |
—
|
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: establish both identity and employment authorization | Statement: [Form I-9, listAPurpose, establish both identity and employment authorization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: listAPurpose Context triple: [Form I-9, listAPurpose, establish both identity and employment authorization]
-
A.
listsMeans
Indicates that one entity enumerates or specifies the meaning, definition, or interpretation of another entity.
-
B.
listsGiant
Indicates that one entity enumerates or catalogs another entity that is characterized as a giant.
-
C.
listType
Indicates that one entity specifies the classification or category type of a list associated with another entity.
-
D.
listsSecurity
Indicates that an entity specifies or enumerates security-related items, settings, or attributes associated with another entity.
-
E.
listedWith
Indicates that an entity is included as an item or entry within a particular list, catalog, or collection.
- 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_69c68811dd1c8190ac460bb39e64e1f0 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea552a688190a00f5d0ad982f787 |
completed | March 27, 2026, 8:36 p.m. |
| PD | Predicate disambiguation | batch_69c6e7644648819096a5e2de5d0dbe97 |
completed | March 27, 2026, 8:24 p.m. |
| PDg | Predicate description generation | batch_69c6ea539f5c81908001524149903559 |
completed | March 27, 2026, 8:36 p.m. |
Created at: March 27, 2026, 2:54 p.m.