Triple
T23719983
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Château de Compiègne |
E586112
|
entity |
| Predicate | majorRebuildingReignOf |
P103248
|
FINISHED |
| Object | Louis XV of France |
—
|
NE NERFINISHED |
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: Louis XV of France | Statement: [Château de Compiègne, majorRebuildingReignOf, Louis XV of France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorRebuildingReignOf Context triple: [Château de Compiègne, majorRebuildingReignOf, Louis XV of France]
-
A.
rebuiltInDynasty
Indicates that something was reconstructed or significantly renovated during a specified dynasty.
-
B.
modifiedDuringReignOf
chosen
Indicates that an entity was altered, updated, or changed while a particular ruler or authority was in power.
-
C.
rebuiltAsPalace
Indicates that a structure or building was reconstructed or transformed into a palace.
-
D.
constructionReignOf
Indicates that a construction activity or project occurred during the reign or rule of a particular authority or leader.
-
E.
builtDuringReignOf
Indicates that something was constructed while a particular ruler or authority was in power.
- 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_69e24906fb108190a6898751e46bdc11 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b77e2dc081908aef7a4c9b188dbd |
completed | April 29, 2026, 7:47 a.m. |
| PD | Predicate disambiguation | batch_69f155e4b1148190836ede4741dcb888 |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 7 p.m.