Triple
T15890194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Medieval Monuments in Kosovo |
E385295
|
entity |
| Predicate | themeOfFrescoes |
P15999
|
FINISHED |
| Object | Christian religious scenes |
—
|
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: Christian religious scenes | Statement: [Medieval Monuments in Kosovo, themeOfFrescoes, Christian religious scenes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: themeOfFrescoes Context triple: [Medieval Monuments in Kosovo, themeOfFrescoes, Christian religious scenes]
-
A.
hasFrescoes
Indicates that something contains or is adorned with fresco paintings as part of its structure or decoration.
-
B.
hasMuralsDepicting
Indicates that one entity contains or features murals that visually represent or portray another entity.
-
C.
artisticTheme
chosen
Indicates the central artistic subject, concept, or motif that characterizes or is expressed by a creative work.
-
D.
iconographicSubject
Indicates that one entity serves as the depicted subject or theme represented in the iconography of another entity.
-
E.
culturalThemes
Indicates that there is a relationship between entities where one embodies, expresses, or is associated with particular cultural themes present in or derived from the other.
- 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_69d86da5b800819083a31be937d738b0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4d08f481909f38b75e3f42d9ab |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142ca3b208190946c3aa4c1e6087c |
completed | April 16, 2026, 8:12 p.m. |
Created at: April 10, 2026, 4:51 a.m.