Triple
T18918276
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chapelle Saint-Michel islet |
E462777
|
entity |
| Predicate | hasBuildingTypeOnSite |
P50464
|
FINISHED |
| Object | Catholic chapel |
—
|
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: Catholic chapel | Statement: [Chapelle Saint-Michel islet, hasBuildingTypeOnSite, Catholic chapel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBuildingTypeOnSite Context triple: [Chapelle Saint-Michel islet, hasBuildingTypeOnSite, Catholic chapel]
-
A.
containsBuildingType
chosen
Indicates that a location or area includes at least one building of the specified type.
-
B.
containsBuilding
Indicates that one location or area includes a building within its boundaries.
-
C.
hasBuildingClass
Indicates that a building is categorized as belonging to a specific building class or type.
-
D.
hasResidentialBuildingsType
Indicates that an entity is associated with a specific type or category of residential buildings.
-
E.
buildingType
Indicates the specific category or function that characterizes what kind of building something is.
- 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_69d8dcfdbbb881909964fa5a75bd0b48 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c62884988190a362ada1a0a47134 |
completed | April 20, 2026, 6:22 a.m. |
| PD | Predicate disambiguation | batch_69e4a2e9e6488190ba8df92c8058ed88 |
completed | April 19, 2026, 9:39 a.m. |
Created at: April 10, 2026, 11:59 a.m.