Triple
T10391043
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. Paul’s Cathedral Choir School |
E244891
|
entity |
| Predicate | primaryPupils |
P70047
|
FINISHED |
| Object | boy choristers of St Paul’s Cathedral |
—
|
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: boy choristers of St Paul’s Cathedral | Statement: [St. Paul’s Cathedral Choir School, primaryPupils, boy choristers of St Paul’s Cathedral]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryPupils Context triple: [St. Paul’s Cathedral Choir School, primaryPupils, boy choristers of St Paul’s Cathedral]
-
A.
primarySchool
Indicates that one entity serves as the primary (elementary) school attended by, associated with, or designated for the other entity.
-
B.
primaryStudents
Indicates that the related entities are students enrolled at the primary or elementary education level.
-
C.
primary
Indicates that the referenced entity is the main or most important one among a set of related entities.
-
D.
primaryStudentType
Indicates the main or most characteristic type or category of student associated with an entity.
-
E.
primaryStudentBody
chosen
Indicates that one entity serves as the main group of enrolled students associated with an educational institution or program.
- 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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9b4f7d08190bcb16d3b4c8f22ad |
completed | April 7, 2026, 11:25 a.m. |
| PD | Predicate disambiguation | batch_69d4dfb0e7a88190bec0b7a52c70dfe2 |
completed | April 7, 2026, 10:42 a.m. |
Created at: April 6, 2026, 12:06 p.m.