Triple
T9505687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SS-20 Saber |
E229262
|
entity |
| Predicate | rangeCategoryINF |
P4679
|
FINISHED |
| Object | 500–5500 kilometers |
—
|
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: 500–5500 kilometers | Statement: [SS-20 Saber, rangeCategoryINF, 500–5500 kilometers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rangeCategoryINF Context triple: [SS-20 Saber, rangeCategoryINF, 500–5500 kilometers]
-
A.
rangeRestricted
Indicates that the relationship or action applies only within a specified, limited subset of a broader domain or scope.
-
B.
range
chosen
Indicates that a value, property, or effect extends between specified limits or over a specified interval or scope.
-
C.
rangeType
Indicates the type or category of values that can appear in the range (output) position of a property or relation.
-
D.
rangeVariant
Indicates that one entity is a variant or alternative form within the value range defined or covered by another entity.
-
E.
rangeOf
Indicates that one entity specifies the set of possible values (range) that another entity’s outputs or properties can take.
- 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_69ca847611c48190a28c028644198c75 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9852b7e48190a8f69cbde10d2858 |
completed | April 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69cca567ca448190bf4bcce8ce7dd54f |
completed | April 1, 2026, 4:56 a.m. |
Created at: March 30, 2026, 7:57 p.m.