Triple
T20789207
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roscomare Road Elementary School |
E511724
|
entity |
| Predicate | servesFamiliesFrom |
P38240
|
FINISHED |
| Object | affluent Bel Air neighborhood |
—
|
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: affluent Bel Air neighborhood | Statement: [Roscomare Road Elementary School, servesFamiliesFrom, affluent Bel Air neighborhood]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesFamiliesFrom Context triple: [Roscomare Road Elementary School, servesFamiliesFrom, affluent Bel Air neighborhood]
-
A.
servesFamily
Indicates that an entity provides food, services, or accommodations suitable for families, typically welcoming and catering to family groups.
-
B.
servesNearbyCommunities
Indicates that an entity provides services or support to communities located in its surrounding area.
-
C.
servesMilitaryFamilies
Indicates that an entity provides services, support, or resources specifically to families of military personnel.
-
D.
serviceDesignationFamily
Indicates that one service designation is part of the same family or grouping as another, reflecting a shared classification or closely related category.
-
E.
servesUsersFrom
chosen
Indicates that an entity provides services or resources to users originating from or associated with a specified source or location.
- 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_69e0b4cb83948190bd57bec21d78ed53 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c28f0e1081909f18dddfc6ec084c |
completed | April 21, 2026, 12:19 a.m. |
| PD | Predicate disambiguation | batch_69e5c0575b1c81908d010223fcd1213e |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:38 p.m.