Triple
T3343037
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M777 howitzer |
E70301
|
entity |
| Predicate | loading |
P25802
|
FINISHED |
| Object | separate-loading ammunition |
—
|
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: separate-loading ammunition | Statement: [M777 howitzer, loading, separate-loading ammunition]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: loading Context triple: [M777 howitzer, loading, separate-loading ammunition]
-
A.
loadingMechanism
chosen
Indicates the method or system by which something is loaded into or onto another object or structure.
-
B.
loadingGauge
Indicates the clearance limits or spatial envelope within which a vehicle or load must fit to safely pass through infrastructure such as tunnels, bridges, or platforms.
-
C.
holding
Indicates that one entity is physically grasping, carrying, or keeping another entity in its possession or control.
-
D.
down
Indicates that one entity is located at a lower position or level relative to another entity or reference point.
-
E.
boarding
Indicates that one entity is getting onto or entering a vehicle, vessel, or similar conveyance associated with 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_69ad85a405e48190b6e68de7cf9f319e |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb1f06f8c8190a6b7c56ac3f5ff07 |
completed | March 8, 2026, 5:29 p.m. |
| PD | Predicate disambiguation | batch_69ada42df1d48190874bb05f95deefde |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:12 p.m.