Triple
T36188239
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parlement de Bretagne |
E1046908
|
entity |
| Predicate | buildingStartOfSeat |
P185714
|
FINISHED |
| Object | 1618 |
—
|
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: 1618 | Statement: [Parlement de Bretagne, buildingStartOfSeat, 1618]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buildingStartOfSeat Context triple: [Parlement de Bretagne, buildingStartOfSeat, 1618]
-
A.
seatBuildingFunction
Indicates that a building or structure serves a seating-related function, such as providing places for people to sit or be accommodated.
-
B.
hasSeatBuilding
Indicates that a seat (or seating area) is located within or belongs to a particular building.
-
C.
establishedAsSeatIn
Indicates that an entity was officially designated or recognized as the administrative or official seat of another entity at a particular time or within a specific context.
-
D.
buildingConstructionStart
Indicates the point in time when the construction work on a building begins.
-
E.
architectOfSeat
Indicates that an entity serves as the architect responsible for the design of a particular seat (e.g., a legislative seat, position, or designated place).
- 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_69f76e3d4fbc81908c159c7beeb4ce00 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c33d59808190b647989a093f3488 |
completed | May 3, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69f7c1b6e7a881908deb96bedb2713f4 |
completed | May 3, 2026, 9:44 p.m. |
| PDg | Predicate description generation | batch_69f7c29cf36481908e472d4dcb5573b9 |
completed | May 3, 2026, 9:48 p.m. |
Created at: May 3, 2026, 4:08 p.m.