Triple
T27360455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basilica of Saint-Barthélemy, Liège |
E685805
|
entity |
| Predicate | baptismalFontArtStyle |
P163487
|
FINISHED |
| Object | Romanesque sculpture |
—
|
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: Romanesque sculpture | Statement: [Basilica of Saint-Barthélemy, Liège, baptismalFontArtStyle, Romanesque sculpture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: baptismalFontArtStyle Context triple: [Basilica of Saint-Barthélemy, Liège, baptismalFontArtStyle, Romanesque sculpture]
-
A.
baptismalFontUsedFor
Indicates that a particular baptismal font is used to perform or conduct a specific baptism or set of baptisms.
-
B.
baptismalFontArtist
Indicates that an entity is the artist or creator responsible for designing or making a particular baptismal font.
-
C.
baptismalFontMaterial
Indicates the material from which a baptismal font is made.
-
D.
hasBaptismalFont
Indicates that a place or structure contains or is equipped with a baptismal font used for performing baptisms.
-
E.
baptisteryArchitecturalStyle
Indicates the architectural style or design tradition according to which a baptistery is built.
- 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_69ef14887c288190931b8431fdbf53c4 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f638d11c988190af7fd4572b08e038 |
completed | May 2, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69f63709e4848190b5cf322e06b23fb6 |
completed | May 2, 2026, 5:40 p.m. |
| PDg | Predicate description generation | batch_69f638344b148190bf0414ef7c5f1f38 |
completed | May 2, 2026, 5:45 p.m. |
Created at: April 27, 2026, 11:53 a.m.