Triple
T19838991
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Assembly of the Republic plenary |
E476672
|
entity |
| Predicate | mainActivityType |
P20949
|
FINISHED |
| Object | legislative debates |
—
|
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: legislative debates | Statement: [Assembly of the Republic plenary, mainActivityType, legislative debates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainActivityType Context triple: [Assembly of the Republic plenary, mainActivityType, legislative debates]
-
A.
majorActivity
Indicates that the related entity performs, participates in, or is primarily associated with a main or most significant activity.
-
B.
hasActivityType
chosen
Indicates the specific kind or category of activity associated with an entity or event.
-
C.
mainPresenter
Indicates that one entity serves as the primary or lead presenter for another entity, such as an event, program, or presentation.
-
D.
mainCurrentAct
Indicates that an entity is currently performing or engaged in its primary or most important action or activity.
-
E.
mainContentType
Indicates the primary type or category of content associated with an entity or resource.
- 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_69d8e51d39d081909bcfafeaaf3d2fcc |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65803bb988190a4e7c0035058feba |
completed | April 20, 2026, 4:44 p.m. |
| PD | Predicate disambiguation | batch_69e5305bda388190a23b7191768107b1 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:50 p.m.