Triple
T31150340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guardian |
E794053
|
entity |
| Predicate | mayBeFormal |
P77628
|
FINISHED |
| Object | legal appointment |
—
|
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: legal appointment | Statement: [Guardian, mayBeFormal, legal appointment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayBeFormal Context triple: [Guardian, mayBeFormal, legal appointment]
-
A.
isLessFormalThan
Indicates that one entity has a lower level of formality or is more casual in style, tone, or usage compared to another entity.
-
B.
formalSetting
Indicates that the associated interaction, event, or context occurs in a formal or official setting governed by explicit social or institutional norms.
-
C.
formalityLevel
Indicates the degree of social or stylistic formality characterizing an interaction, expression, or context between entities.
-
D.
canBeFormalName
chosen
Indicates that something is suitable or valid to be used as a formal or official name.
-
E.
mayForm
Indicates that one entity has the potential or permission to be combined or configured to create, constitute, or result in another entity or structure.
- 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_69f224d41bb48190a5621cd1485e3a30 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f7308a096081909d66a56f3c926806 |
completed | May 3, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69f72a00c5f081908b6539d15baf4e12 |
completed | May 3, 2026, 10:57 a.m. |
Created at: April 29, 2026, 9:06 p.m.