Triple
T4733409
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Federal Home Loan Bank of Topeka |
E105064
|
entity |
| Predicate | typeOfGSE |
P58470
|
FINISHED |
| Object | wholesale bank for housing finance |
—
|
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: wholesale bank for housing finance | Statement: [Federal Home Loan Bank of Topeka, typeOfGSE, wholesale bank for housing finance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfGSE Context triple: [Federal Home Loan Bank of Topeka, typeOfGSE, wholesale bank for housing finance]
-
A.
gutType
Indicates the type or classification of a digestive tract or gut associated with an entity.
-
B.
guthrieClassification
Indicates a categorization relationship where an entity is assigned a class or type according to the Guthrie classification system.
-
C.
oreType
Indicates the specific kind or classification of ore associated with an entity.
-
D.
SCIType
Indicates a classification relationship where an entity is assigned a specific type or category within a scientific or structured information context.
-
E.
O1Biotype
Indicates that an entity has or is classified by a specific biological type or category.
- 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_69bd43ee52048190b81a4f066534ffb3 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6466354481908595f5bb56025cdb |
completed | March 20, 2026, 3:14 p.m. |
| PD | Predicate disambiguation | batch_69bd6221c3b881908604f35f8de6f16b |
completed | March 20, 2026, 3:05 p.m. |
| PDg | Predicate description generation | batch_69bd637e19e081909e415544106c7835 |
completed | March 20, 2026, 3:10 p.m. |
Created at: March 20, 2026, 1:19 p.m.