Triple
T5907324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maison royale de Saint-Louis |
E131370
|
entity |
| Predicate | laterUseOfBuildings |
P47023
|
FINISHED |
| Object | military academy |
—
|
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: military academy | Statement: [Maison royale de Saint-Louis, laterUseOfBuildings, military academy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterUseOfBuildings Context triple: [Maison royale de Saint-Louis, laterUseOfBuildings, military academy]
-
A.
previousBuildingUse
Indicates that a building previously served a specified use or function before its current one.
-
B.
buildingReuseType
Indicates the manner or purpose for which an existing building is reused or repurposed.
-
C.
buildingUsedSince
Indicates that a particular building has been in use starting from a specified point in time.
-
D.
architecturalUse
Indicates how a structure, space, or element is intended to be used or function within an architectural context.
-
E.
laterRepurposedFor
chosen
Indicates that something was originally used for one purpose and subsequently assigned a different, new purpose.
- 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_69c0085864a88190a569c05ff7d65f29 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c03ee10b308190afe38b904ae7c5f7 |
completed | March 22, 2026, 7:11 p.m. |
| PD | Predicate disambiguation | batch_69c0334fcf6481908e8e74105de9d49b |
completed | March 22, 2026, 6:22 p.m. |
Created at: March 22, 2026, 3:59 p.m.