Triple
T20962075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Enrico Scrovegni |
E516271
|
entity |
| Predicate | motivationForCommission |
P76744
|
FINISHED |
| Object | atonement for the sin of usury |
—
|
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: atonement for the sin of usury | Statement: [Enrico Scrovegni, motivationForCommission, atonement for the sin of usury]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: motivationForCommission Context triple: [Enrico Scrovegni, motivationForCommission, atonement for the sin of usury]
-
A.
motivationFor
Indicates that one entity serves as the reason, drive, or incentive behind another entity’s action, state, or occurrence.
-
B.
motivatedByGoal
Indicates that an action, behavior, or state occurs as a result of an intention to achieve a specific goal or desired outcome.
-
C.
commissionReason
chosen
Indicates the reason or justification for which a commission is initiated, assigned, or granted between entities.
-
D.
promotionReason
Indicates the reason or justification for which an entity was promoted to a higher position, status, or level.
-
E.
laterMotivation
Indicates that one event, state, or action serves as a motivation or reason for another event, state, or action that occurs later in time.
- 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_69e0b4fde6c48190af1398e7e734629e |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fb6fd1d48190ad0ec7eb72f84889 |
completed | April 21, 2026, 4:22 a.m. |
| PD | Predicate disambiguation | batch_69e5dbe6976081908abd4e9c8734bae9 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:31 p.m.