Triple
T27819624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ruins of St. Kolumba church |
E702775
|
entity |
| Predicate | incorporatedIntoMuseum |
P52115
|
FINISHED |
| Object | early 21st century |
—
|
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: early 21st century | Statement: [ruins of St. Kolumba church, incorporatedIntoMuseum, early 21st century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: incorporatedIntoMuseum Context triple: [ruins of St. Kolumba church, incorporatedIntoMuseum, early 21st century]
-
A.
inMuseumCollectionSince
chosen
Indicates the date or time from which an item has been part of a museum’s collection.
-
B.
associatedWithMuseum
Indicates a relationship where an entity has a formal or recognized connection to a museum, such as ownership, curation, exhibition, or institutional affiliation.
-
C.
museumHolds
Indicates that a museum possesses, preserves, or has custody of a particular item or collection within its holdings.
-
D.
conversionToMuseum
Indicates that something is being transformed or repurposed into a museum.
-
E.
foundedAsMuseumBy
Indicates that an entity was established or created as a museum by a specific person or organization.
- 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_69ef840ad1e88190b5bff2d1ddec8700 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a931748190a637e631a52bbfaa |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 27, 2026, 5:47 p.m.