Triple
T687468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kato Svanidze |
E13314
|
entity |
| Predicate | marriedToPositionHolder |
P4763
|
FINISHED |
| Object | leader of the Soviet Union |
—
|
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: leader of the Soviet Union | Statement: [Kato Svanidze, marriedToPositionHolder, leader of the Soviet Union]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marriedToPositionHolder Context triple: [Kato Svanidze, marriedToPositionHolder, leader of the Soviet Union]
-
A.
positionOnMarriage
Indicates a person's stance, opinion, or policy regarding the institution or practice of marriage.
-
B.
positionHeldBySpouse
chosen
Indicates that a particular position, role, or office is or was held by the spouse of a given person.
-
C.
marriedInto
Indicates that one entity became connected to another’s family or group through marriage, rather than by birth or prior membership.
-
D.
metSpouseThrough
Indicates that one person became acquainted with and subsequently married their spouse as a result of a particular intermediary person, event, place, or context.
-
E.
positionHeld
Indicates that an entity occupies or has occupied a specific role, job, office, or position within an organization or context.
- 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_69a4933e0f98819097d22766c49b61b8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a0f55f7481909e052a25bd12d455 |
completed | March 1, 2026, 8:26 p.m. |
| PD | Predicate disambiguation | batch_69a49d2048d48190ab99ab59accb6909 |
completed | March 1, 2026, 8:10 p.m. |
Created at: March 1, 2026, 7:36 p.m.