Triple
T31415184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mother Maria |
E801374
|
entity |
| Predicate | supervisesConstructionOf |
P17493
|
FINISHED |
| Object | 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: chapel | Statement: [Mother Maria, supervisesConstructionOf, chapel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supervisesConstructionOf Context triple: [Mother Maria, supervisesConstructionOf, chapel]
-
A.
constructionSupervision
chosen
Indicates that one entity oversees, manages, or inspects the construction activities or process of another entity or project.
-
B.
supervisesFor
Indicates that one entity oversees, directs, or manages the work, activities, or responsibilities of another entity on behalf of a third party or specific purpose.
-
C.
supervisesBy
Indicates that one entity is overseen, directed, or managed under the authority of another entity.
-
D.
builtToOversee
Indicates that one entity was constructed or established for the purpose of supervising, managing, or monitoring another entity or activity.
-
E.
describesConstructionOf
Indicates that one entity provides information or details about how another entity is built, formed, or constructed.
- 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_69f348c0dd648190bf2fd7642f78eb06 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: April 30, 2026, 8:42 p.m.