Triple
T21433726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | reconstructed Berlin Palace facades |
E528752
|
entity |
| Predicate | hasDomeInscriptionLanguage |
P9278
|
FINISHED |
| Object | German |
—
|
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: German | Statement: [reconstructed Berlin Palace facades, hasDomeInscriptionLanguage, German]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDomeInscriptionLanguage Context triple: [reconstructed Berlin Palace facades, hasDomeInscriptionLanguage, German]
-
A.
hasLanguageOnPlaque
Indicates that a specific language appears in the text or inscription displayed on a particular plaque.
-
B.
hasLanternInscription
Indicates that an entity bears or contains an inscription specifically on or associated with a lantern.
-
C.
inscriptionsLanguage
Indicates that the language used in the inscriptions on an object or surface is the specified language.
-
D.
bellInscriptionLanguage
Indicates the language in which the inscription on a bell is written.
-
E.
hasLanguageOn
chosen
Indicates that an entity uses or is associated with a particular language in a specific context, medium, or location.
- 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_69e0c4569fa081908101baa24f8745db |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b5344c048190adfa6f6dd1b453ac |
completed | April 22, 2026, 11:47 a.m. |
| PD | Predicate disambiguation | batch_69e61639ee288190889ffd500d1260f6 |
completed | April 20, 2026, 12:04 p.m. |
Created at: April 16, 2026, 6 p.m.