Triple
T7217057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kuhn, Loeb & Co. |
E149561
|
entity |
| Predicate | financingActivity |
P154
|
FINISHED |
| Object | bond underwriting for railroads |
—
|
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: bond underwriting for railroads | Statement: [Kuhn, Loeb & Co., financingActivity, bond underwriting for railroads]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: financingActivity Context triple: [Kuhn, Loeb & Co., financingActivity, bond underwriting for railroads]
-
A.
fundingContext
Indicates the circumstances, purpose, or conditions under which funding is provided or used in a given relationship or action.
-
B.
funds
chosen
Indicates that one entity provides financial resources or monetary support to another entity or activity.
-
C.
fundingCharacteristics
Indicates the nature, terms, and key attributes of how something is funded or financially supported.
-
D.
finType
Indicates that an entity is of a finite type, meaning it has only a finite number of distinct possible values or elements.
-
E.
fundingFlexibility
Indicates the degree to which the terms, timing, or use of provided funds can be adjusted or reallocated without violating the original funding agreement.
- 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_69c687eca814819095abb52316b1af80 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6e99000dc81908ef4b70729cc00b0 |
completed | March 27, 2026, 8:33 p.m. |
| PD | Predicate disambiguation | batch_69c6e75f84e481909e7866186ae80cff |
completed | March 27, 2026, 8:23 p.m. |
Created at: March 27, 2026, 2:53 p.m.