Triple
T26830771
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oxford reserve crews |
E675493
|
entity |
| Predicate | universityRival |
P14804
|
FINISHED |
| Object | University of Cambridge |
—
|
NE NERFINISHED |
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: University of Cambridge | Statement: [Oxford reserve crews, universityRival, University of Cambridge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: universityRival Context triple: [Oxford reserve crews, universityRival, University of Cambridge]
-
A.
rivalInstitution
chosen
Indicates that one institution is in a state of competition or opposition with another institution.
-
B.
schoolRival
Indicates a competitive or adversarial relationship between two schools, typically in academics, sports, or other institutional activities.
-
C.
campusDistanceBetweenRivals
Indicates the physical distance separating the campuses of two rival institutions.
-
D.
campusLocationOfOneRival
Indicates that one entity is the campus location of another entity that is considered a rival.
-
E.
campusLocationOfOtherRival
Indicates that one campus is located in a place that is home to another institution considered a rival.
- 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_69eee9b776448190993a60b67fcc9545 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f61adc60c88190924d7b71d52851e8 |
completed | May 2, 2026, 3:40 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 5:01 a.m.