Triple
T18316214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Office of Redress Administration |
E438759
|
entity |
| Predicate | compensationPerPerson |
P56119
|
FINISHED |
| Object | 20000 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: 20000 US dollars | Statement: [Office of Redress Administration, compensationPerPerson, 20000 US dollars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: compensationPerPerson Context triple: [Office of Redress Administration, compensationPerPerson, 20000 US dollars]
-
A.
compensationRate
Indicates the rate or amount of payment provided in exchange for a specified unit of work, time, or service.
-
B.
directPaymentAmountPerAdultUSD
Indicates the amount of a direct payment, expressed in U.S. dollars, that is allocated to each adult.
-
C.
providedCompensationAmount
Indicates the specific amount of compensation that was given or agreed to be given in relation to an action, event, or obligation.
-
D.
humanCost
Indicates the extent of harm, suffering, or loss experienced by people as a consequence of an action, event, or decision.
-
E.
reparationAmountPerPerson
chosen
Indicates the specific amount of reparations allocated or owed to each individual person involved.
- 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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5021e61008190a300b6c51976a837 |
completed | April 19, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69e44fe4ee10819086b4142444fca1f5 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:36 a.m.