Triple
T34818845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vera Stravinsky |
E1003710
|
entity |
| Predicate | roleInIgorStravinskyLife |
P203044
|
FINISHED |
| Object | manager of social and domestic affairs |
—
|
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: manager of social and domestic affairs | Statement: [Vera Stravinsky, roleInIgorStravinskyLife, manager of social and domestic affairs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInIgorStravinskyLife Context triple: [Vera Stravinsky, roleInIgorStravinskyLife, manager of social and domestic affairs]
-
A.
marriedToIgorStravinskyFrom
Indicates that an entity was married to Igor Stravinsky starting from a specified point in time.
-
B.
notableComposerRole
Indicates that the subject has a significant or distinguished role as a composer in relation to the object.
-
C.
creatorRoleOfComposer
Indicates that an entity serves in the role of composer as the creator of another entity.
-
D.
roleInSymphony
Indicates the specific function or part an entity performs within the context of a symphony.
-
E.
orchestralRole
Indicates the specific function or position an entity holds within an orchestra (e.g., conductor, principal violin, section player).
- F. None of above. chosen
Provenance (4 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_69f76db717088190811b4e744610f37d |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a01185c46f0819089b4a2ad3c3e2f33 |
completed | May 10, 2026, 11:44 p.m. |
| PD | Predicate disambiguation | batch_6a0117e19e008190870663dd45084416 |
completed | May 10, 2026, 11:42 p.m. |
| PDg | Predicate description generation | batch_6a01185b580c8190a01f65404486cfec |
completed | May 10, 2026, 11:44 p.m. |
Created at: May 3, 2026, 4 p.m.