Triple
T29883962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MAS-36 rifle |
E758957
|
entity |
| Predicate | bayonetStorage |
P99825
|
FINISHED |
| Object | stored reversed under the barrel |
—
|
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: stored reversed under the barrel | Statement: [MAS-36 rifle, bayonetStorage, stored reversed under the barrel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bayonetStorage Context triple: [MAS-36 rifle, bayonetStorage, stored reversed under the barrel]
-
A.
bayonetMount
Indicates that one object is equipped with or designed to accept a bayonet-style mounting connection to another object.
-
B.
hasAmmunitionStorage
Indicates that an entity possesses or is associated with a designated place or facility for storing ammunition.
-
C.
hasScabbard
chosen
Indicates that an item, typically a bladed weapon, is accompanied by or stored in a scabbard designed to hold it.
-
D.
armory
Indicates that an entity serves as a place where weapons, armor, or military equipment are stored, maintained, or supplied for use.
-
E.
armedBy
Indicates that one entity is supplied with weapons, equipment, or armaments 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_69f2245de2f48190a481404896b56254 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f676fb3b9c819097dcd5920e0cd09e |
completed | May 2, 2026, 10:13 p.m. |
| PD | Predicate disambiguation | batch_69f66ac32b60819092290b2de35988d3 |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 29, 2026, 5:59 p.m.