Triple
T19756421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shriners Hospitals for Children – Houston |
E474511
|
entity |
| Predicate | primaryPatientGroup |
P112711
|
FINISHED |
| Object | children |
—
|
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: children | Statement: [Shriners Hospitals for Children – Houston, primaryPatientGroup, children]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryPatientGroup Context triple: [Shriners Hospitals for Children – Houston, primaryPatientGroup, children]
-
A.
primaryPatientType
Indicates the main category or classification of patient that is primarily associated with or targeted by an entity, action, or service.
-
B.
primaryPractitioners
Indicates the entities that are the main or most directly responsible practitioners of a given activity, field, or practice in relation to another entity.
-
C.
primaryClientGroup
chosen
Indicates the main group of clients that an entity primarily serves or is chiefly associated with.
-
D.
primaryUserGroup
Indicates the main or default user group to which a user is primarily assigned or associated.
-
E.
primaryMembers
Indicates that the related entities are the main or most important members within a larger group or organization.
- 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_69d8e51940a0819087bd2996f98da668 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6531afcbc8190bd5364700008f6d8 |
completed | April 20, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69e5305016e08190b9561a96baecb0b8 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:48 p.m.