Triple
T31943650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | V_us |
E815589
|
entity |
| Predicate | approximatelyEquals |
P4460
|
FINISHED |
| Object | sin(Cabibbo angle) |
—
|
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: sin(Cabibbo angle) | Statement: [V_us, approximatelyEquals, sin(Cabibbo angle)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximatelyEquals Context triple: [V_us, approximatelyEquals, sin(Cabibbo angle)]
-
A.
representsApproximately
Indicates that one entity serves as an inexact or close-but-not-exact representation or value of another entity.
-
B.
alignedApproximately
Indicates that two or more entities are positioned or oriented in roughly the same direction or arrangement, allowing for minor deviations or imprecision.
-
C.
containsApproximately
Indicates that one entity holds or includes another entity in a quantity or proportion that is close to, but not exactly, a specified amount.
-
D.
approximates
chosen
Indicates that one entity is close to, but not exactly equal to, the value, form, or behavior of another entity.
-
E.
hasApproximateValue
Indicates that one entity’s value is close to, but not exactly equal to, the value of another entity within an acceptable margin of error.
- 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_69f348f42d188190a33fc8d20ec50517 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fe7eb4b8348190bb19d35766189ed4 |
completed | May 9, 2026, 12:24 a.m. |
| PD | Predicate disambiguation | batch_69fe7c35d2148190ab952e54feda1e76 |
completed | May 9, 2026, 12:13 a.m. |
Created at: May 1, 2026, 12:06 a.m.