Triple
T134109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trinity test site, New Mexico |
E2713
|
entity |
| Predicate | yieldOfTest |
P374
|
FINISHED |
| Object | about 21 kilotons 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: about 21 kilotons of TNT | Statement: [Trinity test site, New Mexico, yieldOfTest, about 21 kilotons of TNT]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yieldOfTest Context triple: [Trinity test site, New Mexico, yieldOfTest, about 21 kilotons of TNT]
-
A.
result
chosen
Indicates that one entity is produced, caused, or brought about as an outcome or consequence of another entity or process.
-
B.
commonTest
Indicates that two or more entities share the same test, testing procedure, or evaluation in common.
-
C.
executedWith
Indicates that an action or process was carried out using, accompanied by, or in conjunction with a specified tool, method, or participant.
-
D.
resultType
Indicates the type or category of outcome that is produced by a given process, action, or operation.
-
E.
bats
Indicates that one entity hits or strikes another entity, typically using a bat or similar implement.
- 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a25788b2688190a45b39447f702551 |
completed | Feb. 28, 2026, 2:48 a.m. |
| PD | Predicate disambiguation | batch_69a25650251c81908a6ea6368cd61198 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.