Triple
T25031083
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | uranium-235 |
E626843
|
entity |
| Predicate | naturalAbundanceInUranium |
P37374
|
FINISHED |
| Object | about 0.72 percent by atoms |
—
|
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: about 0.72 percent by atoms | Statement: [uranium-235, naturalAbundanceInUranium, about 0.72 percent by atoms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: naturalAbundanceInUranium Context triple: [uranium-235, naturalAbundanceInUranium, about 0.72 percent by atoms]
-
A.
naturalAbundance
chosen
Indicates the typical proportion or percentage of a particular isotope or substance as it naturally occurs in a given environment or sample.
-
B.
naturalIsotope
Indicates that one entity is a naturally occurring isotope form of another element or nuclide.
-
C.
uraniumGradeCharacteristic
Indicates that something has a specified grade or quality level in terms of its uranium content or concentration.
-
D.
naturalIsotopesCount
Indicates the number of distinct naturally occurring isotopes associated with an entity.
-
E.
mostAbundantIsotope
Indicates that one isotope of an element is identified as the most frequently occurring (highest natural abundance) among all its isotopes.
- 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_69e2ff2a2c088190be513727ee8bfe78 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f464b4c9b0819085daa00c7c3b8b76 |
completed | May 1, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69f45cfb53f4819099bba48c5057e787 |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 18, 2026, 6:07 a.m.