Triple
T16754254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M67 fragmentation grenade |
E407167
|
entity |
| Predicate | typicalThrowRange |
P13474
|
FINISHED |
| Object | 30 to 40 meters by an average soldier |
—
|
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: 30 to 40 meters by an average soldier | Statement: [M67 fragmentation grenade, typicalThrowRange, 30 to 40 meters by an average soldier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalThrowRange Context triple: [M67 fragmentation grenade, typicalThrowRange, 30 to 40 meters by an average soldier]
-
A.
throwsUpTo
Indicates that an entity propels or sends something in an upward direction toward a specified target or limit.
-
B.
throws
Indicates that one entity propels or hurls another entity or object through space, typically by a deliberate physical action.
-
C.
typicalRange
chosen
Indicates the usual or expected range of values, conditions, or states within which something normally occurs or applies.
-
D.
wasThrownFrom
Indicates that an entity was propelled away or ejected from another entity, typically by a forceful or intentional throwing action.
-
E.
canBeThrownBy
Indicates that one entity is capable of being thrown or launched by another entity.
- 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_69d8839174188190909f190097207065 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3abe6b68c8190a5e2a11973f01b8e |
completed | April 18, 2026, 4:05 p.m. |
| PD | Predicate disambiguation | batch_69e319cbd79c8190a03587a61c18bec0 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:21 a.m.