Triple
T2312598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karabiner 98k |
E51991
|
entity |
| Predicate | rearSightType |
P20282
|
FINISHED |
| Object | tangent leaf |
—
|
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: tangent leaf | Statement: [Karabiner 98k, rearSightType, tangent leaf]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rearSightType Context triple: [Karabiner 98k, rearSightType, tangent leaf]
-
A.
usedIronSights
Indicates that an entity performed an action or engaged in an activity by aiming through iron sights rather than using optical or electronic sights.
-
B.
reticleType
Indicates the specific style or configuration of the aiming reticle used in a targeting or sighting system.
-
C.
sightType
chosen
Indicates the specific kind or category of sight or visual perception associated with an entity or event.
-
D.
gunStabilisation
Indicates that an entity performs or provides stabilization for a gun, reducing its movement or recoil to improve accuracy.
-
E.
eyeRelief
Indicates the distance between an eyepiece and the observer’s eye at which the full field of view can be comfortably seen.
- 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_69a88b0bb30c81908ded03b006d29387 |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abc685f05481909c863b29d1f6bacd |
completed | March 7, 2026, 6:32 a.m. |
| PD | Predicate disambiguation | batch_69abc58e88e481908733fdf79d3f8a15 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:49 p.m.