Triple
T25306685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Family Caregiver Support Program (California) |
E634498
|
entity |
| Predicate | serviceModality |
P129788
|
FINISHED |
| Object | in-person services |
—
|
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: in-person services | Statement: [Family Caregiver Support Program (California), serviceModality, in-person services]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serviceModality Context triple: [Family Caregiver Support Program (California), serviceModality, in-person services]
-
A.
modalityOf
Indicates that one element specifies the manner, mood, or mode in which the action, event, or state expressed by another element is realized or presented.
-
B.
offersModality
Indicates that one entity provides or supports a particular mode, method, or form in which something can be experienced, delivered, or performed.
-
C.
serviceModuleType
Indicates the type or category of a service module associated with an entity or system.
-
D.
serviceDimension
Indicates a relationship where one entity specifies or characterizes a particular dimension, aspect, or facet of a service provided by another entity.
-
E.
modeOfService
chosen
Indicates the manner, method, or channel through which a service is delivered or provided.
- 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_69e75a972c6481909bc11710e8d30a6c |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f606c79ad081908369605f72e65ca6 |
completed | May 2, 2026, 2:14 p.m. |
| PD | Predicate disambiguation | batch_69f602ce79ec8190b8336c2b9de18ac7 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 21, 2026, 1:25 p.m.