Triple
T6596845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anupama Nadella |
E148496
|
entity |
| Predicate | familyFocus |
P63314
|
FINISHED |
| Object | support for children with disabilities |
—
|
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: support for children with disabilities | Statement: [Anupama Nadella, familyFocus, support for children with disabilities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: familyFocus Context triple: [Anupama Nadella, familyFocus, support for children with disabilities]
-
A.
familyAspect
Indicates a relationship where one entity is characterized by a particular familial role, status, or aspect in relation to another entity.
-
B.
family
Indicates a familial relationship or connection between entities, such as being related by blood, marriage, or adoption.
-
C.
familyContext
Indicates that the entities are related or associated within a family or household context, such as kinship, caregiving, or shared domestic life.
-
D.
familyInvolvement
chosen
Indicates that there is participation, engagement, or influence of family members in the context of a particular activity, decision, or situation.
-
E.
familyType
Indicates the specific familial relationship or category that characterizes how the related entities are connected as family.
- 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_69c687e7b8688190811ffee72e096468 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6cc9c6cb0819084fec8e0beb430de |
completed | March 27, 2026, 6:29 p.m. |
| PD | Predicate disambiguation | batch_69c6acfd17388190bd0bb8b2371e7df1 |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:56 p.m.