Triple
T687469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kato Svanidze |
E13314
|
entity |
| Predicate | spousePosition |
P4763
|
FINISHED |
| Object | wife of Joseph Stalin |
—
|
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: wife of Joseph Stalin | Statement: [Kato Svanidze, spousePosition, wife of Joseph Stalin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spousePosition Context triple: [Kato Svanidze, spousePosition, wife of Joseph Stalin]
-
A.
spouseOccupation
Indicates that one person’s spouse has a particular job, profession, or occupation.
-
B.
positionHeldBySpouse
chosen
Indicates that a particular position, role, or office is or was held by the spouse of a given person.
-
C.
spouse
Indicates that two entities are married to each other in a legally or socially recognized partnership.
-
D.
spouseMemberOf
Indicates that a person’s spouse is a member of a specified group, organization, or entity.
-
E.
spouseFamily
Indicates a family relationship formed through marriage, such as between a person and their spouse’s relatives.
- 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.