Triple
T19448936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tønsberg Cathedral |
E486559
|
entity |
| Predicate | hasAltarPiece |
P111990
|
FINISHED |
| Object | altarpiece depicting the Crucifixion |
—
|
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: altarpiece depicting the Crucifixion | Statement: [Tønsberg Cathedral, hasAltarPiece, altarpiece depicting the Crucifixion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAltarPiece Context triple: [Tønsberg Cathedral, hasAltarPiece, altarpiece depicting the Crucifixion]
-
A.
hasMainAltarpiece
chosen
Indicates that an entity (typically a religious building or space) possesses a specific artwork or structure serving as its principal altarpiece.
-
B.
hasAltar
Indicates that one entity possesses, contains, or includes an altar as part of its features or components.
-
C.
hasAltarpieceHeight
Indicates the relationship specifying the height measurement of an altarpiece.
-
D.
hasAltarpiecesInStyle
Indicates that an entity possesses or features altarpieces that are created or designed in a specified artistic style.
-
E.
hasAltarpieceWidth
Indicates the measured horizontal dimension (width) of an altarpiece.
- 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_69d8e8d7ad488190a3373045029b0f3b |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6338be5a48190973d9ecae853900c |
completed | April 20, 2026, 2:09 p.m. |
| PD | Predicate disambiguation | batch_69e4fd6e806081909053f325ba01ab6b |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 1:38 p.m.