Triple
T3358424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M198 howitzer |
E70658
|
entity |
| Predicate | maximumRangeWithStandardHE |
P14301
|
FINISHED |
| Object | 22200 m |
—
|
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: 22200 m | Statement: [M198 howitzer, maximumRangeWithStandardHE, 22200 m]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maximumRangeWithStandardHE Context triple: [M198 howitzer, maximumRangeWithStandardHE, 22200 m]
-
A.
isHighestRangeOf
Indicates that one entity represents the maximum or topmost range or interval within which another entity falls or is categorized.
-
B.
maximumChannelWidth
Indicates the greatest allowable or observed width of a channel in the given context.
-
C.
maximumReach
chosen
Indicates the greatest extent, distance, or limit that something can reach or influence within a given context.
-
D.
hasStandardSubdivisionRange
Indicates that there is a defined range of standard subdivisions applicable to a given entity or classification.
-
E.
operationalRange
Indicates the span of conditions (such as distance, time, or environment) within which a system, device, or process can function effectively and safely.
- 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_69ad85a660c48190998489309a3b4869 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb26523cc819091006fde7beb32e4 |
completed | March 8, 2026, 5:31 p.m. |
| PD | Predicate disambiguation | batch_69ada42fbe7c8190b9f185b5ab985f17 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.