Triple
T37398190
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. Mary’s Preparatory |
E928915
|
entity |
| Predicate | isNonPublic |
P35448
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [St. Mary’s Preparatory, isNonPublic, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isNonPublic Context triple: [St. Mary’s Preparatory, isNonPublic, true]
-
A.
isOnPrivateProperty
Indicates that the subject is located within the boundaries of property that is privately owned and not open for unrestricted public access.
-
B.
isPrivateOrPublic
chosen
Indicates whether something is designated as private or public in terms of its accessibility or visibility.
-
C.
isPublicSymbol
Indicates that something functions as a widely recognized sign, emblem, or representation used in public contexts.
-
D.
isNonlocal
Indicates that the relationship or effect occurs between entities separated in space (or context) without requiring direct, local interaction.
-
E.
isInternal
Indicates that something exists or occurs within the boundaries, structure, or inner context of a specified entity or system, rather than being external to it.
- 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_69f76ebb10c481909b54b9dba263e29f |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb9e1845e881908d19158440cf3b87 |
completed | May 6, 2026, 8:01 p.m. |
| PD | Predicate disambiguation | batch_69fb8d08d6988190a00794ac26078348 |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:16 p.m.