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.