Triple
T23418762
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | World War I reparations |
E560583
|
entity |
| Predicate | initialTotalAmount |
P152178
|
FINISHED |
| Object | 132 billion gold marks |
—
|
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: 132 billion gold marks | Statement: [World War I reparations, initialTotalAmount, 132 billion gold marks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialTotalAmount Context triple: [World War I reparations, initialTotalAmount, 132 billion gold marks]
-
A.
totalInvestment
Indicates the overall amount of resources (typically money) committed to a particular entity, project, or activity, aggregating all individual investments involved.
-
B.
totalGross
Indicates the overall amount of money generated in revenue, typically from all sources over a specified period or for a specific work or event.
-
C.
totalAidAmountUSD
Indicates the total monetary value of aid provided, expressed in U.S. dollars.
-
D.
totalAidAmountAdjusted
Indicates the total amount of aid provided, after applying any relevant adjustments such as corrections, discounts, or recalculations.
-
E.
initialSubscribedCapital
Indicates the amount of capital that parties commit to subscribe at the outset of an agreement, organization, or financial arrangement.
- 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_69e2454cb1108190ab21ada5411a7146 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a5438ac08190a40a3d6402794699 |
completed | April 29, 2026, 6:29 a.m. |
| PD | Predicate disambiguation | batch_69f061ed34288190a2e5e8cae03b0095 |
completed | April 28, 2026, 7:29 a.m. |
| PDg | Predicate description generation | batch_69f07cbbd7488190ab3c8ae7d0fb68bf |
completed | April 28, 2026, 9:24 a.m. |
Created at: April 17, 2026, 5:43 p.m.