Triple
T4993310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Church of Saint-Pierre d’Auxerre |
E112183
|
entity |
| Predicate | hasArtisticWork |
P1572
|
FINISHED |
| Object | sculpted decoration |
—
|
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: sculpted decoration | Statement: [Church of Saint-Pierre d’Auxerre, hasArtisticWork, sculpted decoration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasArtisticWork Context triple: [Church of Saint-Pierre d’Auxerre, hasArtisticWork, sculpted decoration]
-
A.
hasArtisticDiscipline
Indicates that one entity practices, specializes in, or is associated with a particular artistic discipline or field.
-
B.
hasPublicArtwork
chosen
Indicates that a location or entity possesses or features artwork that is accessible to the general public.
-
C.
hasArtisticGenre
Indicates that an entity (such as a work or creation) belongs to or is characterized by a particular artistic genre.
-
D.
exhibitsWorkOf
Indicates that one entity displays or presents the creative works produced by another entity.
-
E.
hasFamousArtwork
Indicates that an entity possesses or is associated with a well-known or widely recognized artwork.
- 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_69bd4432b32c81909f3b3c6bd10f0653 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd74249a8c8190952680aee06a9286 |
completed | March 20, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69bd71492dec8190af4c27a3043b35cc |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:34 p.m.