Triple
T36973934
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Good Delivery gold bars |
E914645
|
entity |
| Predicate | hasTypicalPurity |
P200875
|
FINISHED |
| Object | approximately 999.9 parts per thousand gold |
—
|
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 999.9 parts per thousand gold | Statement: [Good Delivery gold bars, hasTypicalPurity, approximately 999.9 parts per thousand gold]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypicalPurity Context triple: [Good Delivery gold bars, hasTypicalPurity, approximately 999.9 parts per thousand gold]
-
A.
purity
Indicates that an entity possesses a high degree of cleanliness, integrity, or freedom from contamination, corruption, or mixed elements.
-
B.
hasCleanlinessLevel
Indicates the degree or state of cleanliness associated with an entity.
-
C.
isColorlessWhenPure
Indicates that an entity has no color when in its pure, uncontaminated form.
-
D.
purifiedBy
Indicates that something has been cleansed, refined, or made pure through the action or process performed by another agent or method.
-
E.
typeOfPurification
Indicates the specific purification method or process applied to an entity or substance.
- 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_69f76e8d13b4819089af24a47ce092fc |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ffb5c373948190a6606e8caa87a384 |
completed | May 9, 2026, 10:31 p.m. |
| PD | Predicate disambiguation | batch_69ffb261da788190b41399df8ed895e8 |
completed | May 9, 2026, 10:17 p.m. |
| PDg | Predicate description generation | batch_69ffb5c2cef0819087a92a1a5ab694a8 |
completed | May 9, 2026, 10:31 p.m. |
Created at: May 3, 2026, 4:14 p.m.