Triple
T8790087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | G36 assault rifle |
E209139
|
entity |
| Predicate | hasSightingSystem |
P81647
|
FINISHED |
| Object | diopter sights (on some configurations) |
—
|
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: diopter sights (on some configurations) | Statement: [G36 assault rifle, hasSightingSystem, diopter sights (on some configurations)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSightingSystem Context triple: [G36 assault rifle, hasSightingSystem, diopter sights (on some configurations)]
-
A.
sightingSystem
chosen
Indicates a relationship where a system is used to detect, observe, or track targets or objects, typically for monitoring or aiming purposes.
-
B.
sightingState
Indicates the current status or condition of a reported sighting within its tracking or verification process.
-
C.
sightType
Indicates the specific kind or category of sight or visual perception associated with an entity or event.
-
D.
hasCCTV
Indicates that one entity is equipped with or monitored by a CCTV (closed-circuit television) system installed or provided by another entity.
-
E.
hasLookout
Indicates that one entity serves as a lookout or watchful observer for another entity, monitoring for potential events, threats, or changes.
- 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_69ca836168108190bb43d3dc235c1f55 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5f8d25f881908863d636fa57a8a2 |
completed | March 31, 2026, 11:58 p.m. |
| PD | Predicate disambiguation | batch_69cc5c1d48f08190b325a77d4c76d223 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:43 p.m.