Triple
T38554690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Château du Girsberg |
E925210
|
entity |
| Predicate | ruinedSinceCentury |
P102701
|
FINISHED |
| Object | 17th century |
—
|
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: 17th century | Statement: [Château du Girsberg, ruinedSinceCentury, 17th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ruinedSinceCentury Context triple: [Château du Girsberg, ruinedSinceCentury, 17th century]
-
A.
abandonedCentury
Indicates that something or someone ceased to be used, maintained, or inhabited during a particular century.
-
B.
ruinsClearedInCentury
Indicates that the clearing or removal of ruins occurred during a specified century.
-
C.
disappearedByCentury
Indicates the century during which an entity ceased to exist, vanished, or was no longer present.
-
D.
centuryOfDestruction
chosen
Indicates the century during which the destruction of an entity occurred.
-
E.
collapseCentury
Indicates that one time period or event causes or undergoes a breakdown or compression of its century-level temporal distinction, effectively merging or reducing it into a different or broader timeframe.
- 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_69f76eaeb69c8190b367df9330d6f6af |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcd31bd2c0819080fcc54dcbc968ba |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f81cbc8190b4fd3bfc3106c1f3 |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:32 p.m.