Triple
T2782166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treaty of the Pyrenees |
E61720
|
entity |
| Predicate | marriageClause |
P21096
|
FINISHED |
| Object | marriage of Louis XIV and Maria Theresa |
—
|
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: marriage of Louis XIV and Maria Theresa | Statement: [Treaty of the Pyrenees, marriageClause, marriage of Louis XIV and Maria Theresa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marriageClause Context triple: [Treaty of the Pyrenees, marriageClause, marriage of Louis XIV and Maria Theresa]
-
A.
marriageType
Indicates the specific legal or social category of a marriage relationship that exists between two spouses.
-
B.
marries
Indicates that one entity enters into a legally or socially recognized marital union with another entity.
-
C.
marriageCustom
Indicates a culturally recognized set of practices, rules, or traditions that govern how marriages are formed, conducted, or maintained between individuals or groups.
-
D.
marriageContractConductedBy
Indicates that a specific marriage contract or ceremony is formally carried out, officiated, or administered by a particular agent or authority.
-
E.
marriageDocumentedIn
chosen
Indicates that a marriage event is recorded or evidenced in a specific document or source.
- 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_69ab4b7e43c48190997b8fc8fb1663ab |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abddceb9d88190961e30d521a21552 |
completed | March 7, 2026, 8:11 a.m. |
| PD | Predicate disambiguation | batch_69abdd00b65c8190a8ea444308c4fa2b |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 9:57 p.m.