Triple
T12426339
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lieutenant Marion "Cobra" Cobretti |
E296906
|
entity |
| Predicate | weaponCustomization |
P76424
|
FINISHED |
| Object | cobra engraving on pistol grip |
—
|
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: cobra engraving on pistol grip | Statement: [Lieutenant Marion "Cobra" Cobretti, weaponCustomization, cobra engraving on pistol grip]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weaponCustomization Context triple: [Lieutenant Marion "Cobra" Cobretti, weaponCustomization, cobra engraving on pistol grip]
-
A.
weaponDesigner
Indicates that one entity is the creator or designer of a weapon used or associated with another entity.
-
B.
weaponFeature
chosen
Indicates that one entity is a characteristic, attribute, or functional aspect of a weapon.
-
C.
weaponMount
Indicates that one entity serves as a mounting point or support structure for attaching or holding a weapon on another entity.
-
D.
equipmentOption
Indicates that a particular piece or configuration of equipment is available or selected as an option in a given context.
-
E.
weaponControl
Indicates that one entity has authority over, access to, or the ability to direct the use of a weapon 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_69d6ada0640c81908c061d7fb3d47786 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94df948308190ace333230a4a3b38 |
completed | April 10, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69d94d391c548190996a8c698357f273 |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.