Triple
T9020103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | L11 155 mm howitzer |
E215698
|
entity |
| Predicate | standardCaliberClass |
P47473
|
FINISHED |
| Object | NATO-standard 155 mm |
—
|
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: NATO-standard 155 mm | Statement: [L11 155 mm howitzer, standardCaliberClass, NATO-standard 155 mm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: standardCaliberClass Context triple: [L11 155 mm howitzer, standardCaliberClass, NATO-standard 155 mm]
-
A.
natoCaliberClass
Indicates that two ammunition types share the same standardized NATO caliber classification.
-
B.
gunCalibre
Indicates the relationship between a firearm and the calibre (size/diameter) of ammunition it is designed to use.
-
C.
standardUSNATOCaliber
chosen
Indicates that an item’s caliber conforms to the standard ammunition dimensions used by U.S. and NATO military forces.
-
D.
rangeStandardAmmunition
Indicates that the relationship specifies the standard type of ammunition used for a given range or weapon system.
-
E.
munitionWeightCategory
Indicates the classification of a munition based on its weight range or weight-related category.
- 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_69ca83a38aa88190bf1bb80c4548b5e2 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6a421c2c8190abb12c826066fe75 |
completed | April 1, 2026, 12:43 a.m. |
| PD | Predicate disambiguation | batch_69cc5edf84408190aa5f57cb8bfd00e1 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:07 p.m.