Triple
T6696146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wetherby School |
E152754
|
entity |
| Predicate | hasAdmissionsPolicy |
P58
|
FINISHED |
| Object | selective admissions |
—
|
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: selective admissions | Statement: [Wetherby School, hasAdmissionsPolicy, selective admissions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAdmissionsPolicy Context triple: [Wetherby School, hasAdmissionsPolicy, selective admissions]
-
A.
admissionPolicy
chosen
Indicates the rules or criteria governing whether and how entities are allowed to be admitted or granted access.
-
B.
hasAdmission
Indicates that an entity possesses or is associated with a specific admission event, record, or status (such as being admitted to a place, program, or institution).
-
C.
hasSubmissionPolicy
Indicates that an entity is associated with a specific set of rules or conditions governing how submissions to it must be made.
-
D.
controlsAdmissionsFor
Indicates that one entity has authority or responsibility over managing and deciding admissions for another entity.
-
E.
hasPolicySupport
Indicates that one entity provides endorsement, backing, or approval for a specific policy associated with another entity.
- 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_69c6880687b08190805278b504d1c92c |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6b5ed99e48190970805225458ce82 |
completed | March 27, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69c6ad0e1d348190af1762ea1951038e |
completed | March 27, 2026, 4:15 p.m. |
Created at: March 27, 2026, 2:05 p.m.