Triple
T33766845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark 53 nuclear bomb |
E865252
|
entity |
| Predicate | lastUnitsRetired |
P120638
|
FINISHED |
| Object | 1997 |
—
|
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: 1997 | Statement: [Mark 53 nuclear bomb, lastUnitsRetired, 1997]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastUnitsRetired Context triple: [Mark 53 nuclear bomb, lastUnitsRetired, 1997]
-
A.
lastActiveShipDecommissionedYear
Indicates the calendar year in which the most recently active ship in a given context was officially decommissioned.
-
B.
scrappedUnits
chosen
Indicates that certain units have been discarded or removed from use, typically due to damage, defects, or obsolescence.
-
C.
retiredFromUSMilitary
Indicates that an individual previously served in the United States military and has formally ended their military career or service.
-
D.
decommissionedFromUSN
Indicates that something was formally retired or removed from active service in the United States Navy.
-
E.
retiredFromUSMCFrontlineService
Indicates that an individual has ended their active frontline duty service in the United States Marine Corps.
- 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_69f3498d3b748190aa3c4006c1f32f38 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6ffbad8848190867c2988c0ceb84f |
completed | May 3, 2026, 7:56 a.m. |
| PD | Predicate disambiguation | batch_69f6fc5740fc81909774a4f65201a3ff |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:45 a.m.