Triple
T622385
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poznań |
E14540
|
entity |
| Predicate | isAcademicCenter |
P17806
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Poznań, isAcademicCenter, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isAcademicCenter Context triple: [Poznań, isAcademicCenter, yes]
-
A.
isEducationalCenterOf
Indicates that an institution functions as the primary educational center serving, representing, or associated with a particular area, organization, or group.
-
B.
centralInstitutionOf
Indicates that one institution serves as the primary or main institutional center for another entity, such as an organization, system, or region.
-
C.
hasAcademicAffiliation
Indicates that an entity is formally associated with an academic institution, such as through employment, enrollment, or official collaboration.
-
D.
isPublicInstitutionCampus
Indicates that a given campus belongs to or is operated by a public (state- or government-run) institution.
-
E.
isPublicInstitution
Indicates that an entity operates as a publicly governed or state-funded institution, typically serving the general public under public law or oversight.
- F. None of above. chosen
Provenance (4 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_69a4934b17c881909ace8270e8ddd202 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49e402d9c8190936896e3ebb6edc5 |
completed | March 1, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69a49d0069d0819087c83b608f6fc053 |
completed | March 1, 2026, 8:09 p.m. |
| PDg | Predicate description generation | batch_69a49e2107548190af0c1d67cfa475d1 |
completed | March 1, 2026, 8:14 p.m. |
Created at: March 1, 2026, 7:35 p.m.