Triple
T4859418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treaty of Neuilly-sur-Seine |
E108617
|
entity |
| Predicate | reparationsAmount |
P19678
|
FINISHED |
| Object | 2250000000 gold francs |
—
|
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: 2250000000 gold francs | Statement: [Treaty of Neuilly-sur-Seine, reparationsAmount, 2250000000 gold francs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reparationsAmount Context triple: [Treaty of Neuilly-sur-Seine, reparationsAmount, 2250000000 gold francs]
-
A.
reparationAmountPerPerson
Indicates the specific amount of reparations allocated or owed to each individual person involved.
-
B.
reparationsType
Indicates the specific category or form of reparations involved in a reparative action or obligation between entities.
-
C.
awardAmount
Indicates the specific quantity or value of an award that is granted in the context of a particular awarding event or relationship.
-
D.
warIndemnityAmount
chosen
Indicates the amount of financial compensation required or paid as indemnity as a result of a war or armed conflict.
-
E.
owedMoneyTo
Indicates that one entity has a financial obligation or debt that must be paid to another entity.
- 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_69bd440b965081908b0557721cae6338 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6d5c92148190a314707bdd3ff30f |
completed | March 20, 2026, 3:53 p.m. |
| PD | Predicate disambiguation | batch_69bd6c27334481909ba8ac80854f7d8e |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:26 p.m.