Triple
T6569077
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Musée d’Art et d’Archéologie de Cluny |
E155386
|
entity |
| Predicate | buildingOrigin |
P61698
|
FINISHED |
| Object | medieval monastery |
—
|
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: medieval monastery | Statement: [Musée d’Art et d’Archéologie de Cluny, buildingOrigin, medieval monastery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buildingOrigin Context triple: [Musée d’Art et d’Archéologie de Cluny, buildingOrigin, medieval monastery]
-
A.
constructionCompanyOrigin
Indicates that a construction company originates from, or is based in, a particular geographic location or jurisdiction.
-
B.
placeBuilt
Indicates that a structure or facility was constructed at a specific location.
-
C.
builtInThe
Indicates that something was constructed or created within a specified location, structure, or context.
-
D.
architecturalOrigin
chosen
Indicates the place, style, or tradition from which an architectural work or design originates.
-
E.
builtNear
Indicates that one entity was constructed at a location geographically close to another entity.
- 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_69c688151254819080387f87deab8fa7 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6cc9c6cb0819084fec8e0beb430de |
completed | March 27, 2026, 6:29 p.m. |
| PD | Predicate disambiguation | batch_69c6acf93cb48190b54f5dd6febd34dc |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:53 p.m.