Triple
T36838978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KfW Bankengruppe |
E910350
|
entity |
| Predicate | shareOfOwnershipOfFederalGovernment |
P7882
|
FINISHED |
| Object | 80% |
—
|
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: 80% | Statement: [KfW Bankengruppe, shareOfOwnershipOfFederalGovernment, 80%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shareOfOwnershipOfFederalGovernment Context triple: [KfW Bankengruppe, shareOfOwnershipOfFederalGovernment, 80%]
-
A.
federalShareOfStock
chosen
Indicates the proportion or amount of stock in an entity that is owned or held by the federal government.
-
B.
sharesFederalGovernmentWith
Indicates that two political entities are governed under the same overarching federal government system.
-
C.
typicalFederalShare
Indicates the usual proportion of costs or funding that is covered by the federal government in a given program or arrangement.
-
D.
sharesSubjectsWithCentralGovernment
Indicates that an entity has the same or overlapping areas of authority, responsibility, or policy subjects as the central government.
-
E.
federalGovernmentEntity
Indicates that the subject is an organization or body that forms part of a national-level (federal) government structure.
- 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_69f76e7f65a881908651b702da592b6d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a00a2f0d1588190a936ea7df0ef0464 |
completed | May 10, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_6a00a28ccd94819085b5e123f5a4769e |
completed | May 10, 2026, 3:21 p.m. |
Created at: May 3, 2026, 4:13 p.m.