Triple
T12209365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castle Bravo |
E290915
|
entity |
| Predicate | predictedYield |
P32569
|
FINISHED |
| Object | 5 megatons of TNT |
—
|
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: 5 megatons of TNT | Statement: [Castle Bravo, predictedYield, 5 megatons of TNT]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predictedYield Context triple: [Castle Bravo, predictedYield, 5 megatons of TNT]
-
A.
yieldPotential
chosen
Indicates the expected amount or capacity of output, production, or benefit that something can generate under given conditions.
-
B.
predictedIn
Indicates that something has been forecast, anticipated, or estimated to occur within or as part of a specified context, time, or situation.
-
C.
predictionType
Indicates the kind or category of prediction being made about an entity or event.
-
D.
predictedEffect
Indicates that one entity is expected to cause, influence, or result in a particular outcome or consequence for another entity.
-
E.
predictionHorizon
Indicates the temporal extent into the future over which a prediction or forecast is intended to apply.
- 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_69d6ab65923081909acfc61b7a612233 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d920e312708190b4aede2e21f5f697 |
completed | April 10, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69d91c3d669c81908eea7ad61122d275 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:51 p.m.