Triple
T36960416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Shotgun |
E914292
|
entity |
| Predicate | reloadType |
P41759
|
FINISHED |
| Object | break-action reload |
—
|
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: break-action reload | Statement: [Super Shotgun, reloadType, break-action reload]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reloadType Context triple: [Super Shotgun, reloadType, break-action reload]
-
A.
refreshType
Indicates the manner or category of update applied to an entity, such as whether it is a full, partial, or incremental refresh.
-
B.
loadType
chosen
Indicates the manner or category of how something is loaded, such as the method, configuration, or type of loading applied in a given context.
-
C.
reloadTime
Indicates the amount of time required for something (typically a weapon, tool, or system) to be reloaded and made ready for use again.
-
D.
rebuildType
Indicates the type or category of rebuilding or reconstruction process applied to an entity.
-
E.
loader
Indicates a relationship where an entity is responsible for loading or placing items, data, or resources into another system, container, or context.
- 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_69f76e8c498c8190b2842db80aea8b3b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fa0a7b00948190a257273d9968c5d7 |
completed | May 5, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69f9fec9c9488190ae2a349651a02782 |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:13 p.m.