Triple
T32911397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elmelunde Church |
E841885
|
entity |
| Predicate | frescoesKnownAs |
P23612
|
FINISHED |
| Object |
Elmelunde Master frescoes
The Elmelunde Master frescoes are a renowned series of late medieval wall paintings in Danish churches, notable for their distinctive style and vivid biblical and moral scenes.
|
E2027887
|
NE FINISHED |
How this triple was built (3 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: Elmelunde Master frescoes | Statement: [Elmelunde Church, frescoesKnownAs, Elmelunde Master frescoes]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Elmelunde Master frescoes Triple: [Elmelunde Church, frescoesKnownAs, Elmelunde Master frescoes]
Generated description
The Elmelunde Master frescoes are a renowned series of late medieval wall paintings in Danish churches, notable for their distinctive style and vivid biblical and moral scenes.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frescoesKnownAs Context triple: [Elmelunde Church, frescoesKnownAs, Elmelunde Master frescoes]
-
A.
frescoesDate
Indicates that a fresco is associated with a specific date or time period of its creation or execution.
-
B.
hasFrescoes
chosen
Indicates that something contains or is adorned with fresco paintings as part of its structure or decoration.
-
C.
hasWallPaintingsOn
Indicates that wall paintings are present on or applied to a specified surface or structure.
-
D.
ceilingFrescoTitle
Indicates that one entity is the title assigned to a ceiling fresco associated with another entity.
-
E.
hasMuralsDepicting
Indicates that one entity contains or features murals that visually represent or portray another entity.
- F. None of above.
Provenance (6 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_69f34946a5208190bbd79f0fec4323bd |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d74b20a48190900dda1014cc13a8 |
completed | May 3, 2026, 5:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a34c69978d08190acd871e2e3ce7b1b |
completed | June 19, 2026, 4:33 a.m. |
| NEDg | Description generation | batch_6a34c8226bac81909eed319bf6b97197 |
completed | June 19, 2026, 4:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a34c93dd1d48190b67b29c885246998 |
completed | June 19, 2026, 4:44 a.m. |
| PD | Predicate disambiguation | batch_69f6d26f27dc8190ae426a3e1573933e |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:19 a.m.