Triple
T9336620
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georg Forster Research Fellowship |
E224658
|
entity |
| Predicate | locationOfResearch |
P21545
|
FINISHED |
| Object | universities in Germany |
—
|
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: universities in Germany | Statement: [Georg Forster Research Fellowship, locationOfResearch, universities in Germany]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationOfResearch Context triple: [Georg Forster Research Fellowship, locationOfResearch, universities in Germany]
-
A.
countryOfResearch
Indicates the country where the research activity was primarily conducted or based.
-
B.
researchSite
chosen
Indicates that a location serves as a site where research or investigative studies are conducted or based.
-
C.
researchCenter
Indicates that one entity functions as a research center associated with, operated by, or focused on the other entity.
-
D.
nearResearchCluster
Indicates that one entity is located in close physical proximity to a designated research cluster or research-focused area.
-
E.
homeInstitutionLocation
Indicates the geographic place where an entity’s primary or home institution is located.
- 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_69ca84286fcc81909f6e7fd7a7e862a2 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd37f161e481908e23c1ec7e5fcf97 |
completed | April 1, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69cc7a66aef08190b8d668cff5b04f5f |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:40 p.m.