Triple
T572787
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trinity College, Cambridge |
E13697
|
entity |
| Predicate | previousAdmissionPolicy |
P58
|
FINISHED |
| Object | men only |
—
|
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: men only | Statement: [Trinity College, Cambridge, previousAdmissionPolicy, men only]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousAdmissionPolicy Context triple: [Trinity College, Cambridge, previousAdmissionPolicy, men only]
-
A.
admissionPolicy
chosen
Indicates the rules or criteria governing whether and how entities are allowed to be admitted or granted access.
-
B.
admissionOrder
Indicates the sequence or priority in which admissions occur or are processed relative to one another.
-
C.
reservationPolicy
Indicates the rules or conditions governing how reservations are made, modified, or canceled between parties.
-
D.
governingPolicy
Indicates that one entity serves as the authoritative policy or set of rules that directs, constrains, or regulates the behavior, operation, or decisions of another entity.
-
E.
positionOnReadmission
Indicates the stance, policy, or viewpoint an entity holds regarding the readmission of another entity (e.g., a person, group, or state).
- 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_69a4933fa4d88190a7949cc83c08c5c1 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49b49bad88190bc73d31a317c0ef4 |
completed | March 1, 2026, 8:02 p.m. |
| PD | Predicate disambiguation | batch_69a494c4969c819080375d08f9eec50c |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.