Triple
T25053255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Atkinson |
E627441
|
entity |
| Predicate | academicWorkInstitution |
P1203
|
FINISHED |
| Object | St John’s College, Durham |
—
|
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: St John’s College, Durham | Statement: [David Atkinson, academicWorkInstitution, St John’s College, Durham]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: academicWorkInstitution Context triple: [David Atkinson, academicWorkInstitution, St John’s College, Durham]
-
A.
workInstitution
chosen
Indicates that an entity is employed by or works at a particular institution.
-
B.
inInstitution
Indicates that an entity is located within, belongs to, or is formally associated with a particular institution.
-
C.
academicAffiliationOfInstitution
Indicates that an institution is academically affiliated with, or formally connected to, another institution.
-
D.
academicInstitutionType
Indicates the specific category or kind of academic institution an entity is classified as (e.g., university, college, high school).
-
E.
associatedInstitution
Indicates that an entity has a formal connection or affiliation with a particular institution.
- 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_69e2ff2c45f48190afa28369f1df6786 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f46d3f35848190b56a4373c97a7d64 |
completed | May 1, 2026, 9:07 a.m. |
| PD | Predicate disambiguation | batch_69f4683472ec8190a483b3b8afe71720 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 18, 2026, 6:09 a.m.