Triple
T20733858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bernie Madoff |
E509638
|
entity |
| Predicate | estimatedPrincipalLoss |
P141300
|
FINISHED |
| Object | approximately 17 to 20 billion US dollars |
—
|
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: approximately 17 to 20 billion US dollars | Statement: [Bernie Madoff, estimatedPrincipalLoss, approximately 17 to 20 billion US dollars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: estimatedPrincipalLoss Context triple: [Bernie Madoff, estimatedPrincipalLoss, approximately 17 to 20 billion US dollars]
-
A.
lossType
Indicates the specific category or nature of a loss associated with an entity or event.
-
B.
causedLossOf
Indicates that one entity brought about or was responsible for another entity experiencing a loss.
-
C.
durabilityLossRate
Indicates the rate at which an entity’s durability decreases over time or use.
-
D.
estimatedUsing
Indicates that one entity’s value, state, or outcome is derived by applying an estimation method, model, or procedure based on another entity.
-
E.
significantLoss
Indicates that an entity has experienced a major or substantial decrease in value, quantity, or status beyond a normal or minor loss.
- 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_69e0b4c589c08190834fb5d86d0efa2b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1ef3040819085c8056e75571104 |
completed | April 21, 2026, 12:16 a.m. |
| PD | Predicate disambiguation | batch_69e5c04b31248190b9b9d91b5cb854e3 |
completed | April 20, 2026, 5:57 a.m. |
| PDg | Predicate description generation | batch_69e5c3cbe5788190b7ace43bfdac2ef6 |
completed | April 20, 2026, 6:12 a.m. |
Created at: April 16, 2026, 12:31 p.m.