Triple
T29104109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marina Severa |
E736715
|
entity |
| Predicate | marriageToValentinianI |
P46634
|
FINISHED |
| Object | ended before 370s |
—
|
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: ended before 370s | Statement: [Marina Severa, marriageToValentinianI, ended before 370s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marriageToValentinianI Context triple: [Marina Severa, marriageToValentinianI, ended before 370s]
-
A.
marriageToConstantiusGallus
Indicates a marital relationship in which one entity is married to Constantius Gallus.
-
B.
marriedToEmperor
chosen
Indicates that one entity is the spouse of an emperor, signifying a marital relationship to a reigning or titled emperor.
-
C.
marriageFormedBy
Indicates that a marriage relationship was created or brought into existence by a specific event, action, or process.
-
D.
rivalForMarriageOf
Indicates that one entity is a romantic competitor with another entity for the opportunity to marry a specific third entity.
-
E.
formedByMarriageOf
Indicates that something (typically a family, union, or legal entity) comes into existence as a result of the marriage between two 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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f7221dc9a88190bb8194fcc29c42bc |
completed | May 3, 2026, 10:23 a.m. |
| PD | Predicate disambiguation | batch_69f72153a9188190b02adc84e1be4af8 |
completed | May 3, 2026, 10:20 a.m. |
Created at: April 28, 2026, 11:14 a.m.