Triple
T28017535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mazarin’s nieces |
E707587
|
entity |
| Predicate | marriagePolicyDirectedBy |
P99052
|
FINISHED |
| Object | Cardinal Mazarin |
—
|
NE NERFINISHED |
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: Cardinal Mazarin | Statement: [Mazarin’s nieces, marriagePolicyDirectedBy, Cardinal Mazarin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marriagePolicyDirectedBy Context triple: [Mazarin’s nieces, marriagePolicyDirectedBy, Cardinal Mazarin]
-
A.
marriageDepictedIn
Indicates that a specific marriage is represented or shown within a particular work, medium, or depiction.
-
B.
maritalPolicy
chosen
Indicates a relationship where an authority or institution defines rules, conditions, or norms governing marriage between individuals.
-
C.
marriageResolvedBy
Indicates that a marital relationship between two parties has been formally concluded or dissolved through a specific resolving action or process (e.g., divorce, annulment).
-
D.
marriageFormedBy
Indicates that a marriage relationship was created or brought into existence by a specific event, action, or process.
-
E.
resultedInMarriageTo
Indicates that one event, action, or circumstance led to or caused a marriage to occur between the related entities.
- 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_69ef96baf3a881909a2b63844185dddd |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 27, 2026, 8:07 p.m.