Triple
T16939056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Operation Ranger |
E410902
|
entity |
| Predicate | minimumYield |
P65817
|
FINISHED |
| Object | 1 kiloton 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: 1 kiloton of TNT | Statement: [Operation Ranger, minimumYield, 1 kiloton of TNT]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: minimumYield Context triple: [Operation Ranger, minimumYield, 1 kiloton of TNT]
-
A.
requiresLowerMaximumYields
Indicates that one entity imposes a constraint on another such that the allowed or achievable maximum yields must be reduced.
-
B.
minimumMass
Indicates the smallest mass value that an entity or system is required, allowed, or observed to have within a given context.
-
C.
minimumGrant
Indicates that there is a lowest allowable or required amount of a grant associated with an entity or agreement.
-
D.
yieldLevel
Indicates the degree or amount of output or production resulting from a process, resource, or entity.
-
E.
minimumLevel
chosen
Indicates that one entity specifies the lowest allowable or required level, degree, or threshold at which another entity, condition, or action becomes valid or applicable.
- 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_69d886c886688190967be07322597ac9 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cf2c44288190a105761ae646989e |
completed | April 18, 2026, 6:36 p.m. |
| PD | Predicate disambiguation | batch_69e32b9aa8748190b248890aca86753d |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:31 a.m.