Triple
T6904846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States gold policy |
E159785
|
entity |
| Predicate | revaluedGoldPrice |
P28196
|
FINISHED |
| Object | 38 US dollars per troy ounce in 1972 |
—
|
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: 38 US dollars per troy ounce in 1972 | Statement: [United States gold policy, revaluedGoldPrice, 38 US dollars per troy ounce in 1972]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: revaluedGoldPrice Context triple: [United States gold policy, revaluedGoldPrice, 38 US dollars per troy ounce in 1972]
-
A.
previousOfficialGoldPrice
Indicates that one value is the immediately preceding officially set gold price relative to another value or time.
-
B.
changedGoldPriceTo
chosen
Indicates that an entity caused the gold price to be updated from its previous value to a new specified value.
-
C.
previousGoldPurity
Indicates that one entity represents the gold purity value that applied to another entity at an earlier time or in a prior state.
-
D.
standardGoldContent
Indicates the specified standard or required amount of gold contained in something, typically as a measure of purity or value.
-
E.
wasDevaluedIn
Indicates that the value or worth of an entity was reduced during a specified event, time period, or context.
- 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_69c68839ccb88190b4aa5cc1aca3448f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d989c13081908a2e346cde9e3a50 |
completed | March 27, 2026, 7:24 p.m. |
| PD | Predicate disambiguation | batch_69c6d7b7681481909ec50509b19fcf81 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:25 p.m.