Triple

T26877048
Position Surface form Disambiguated ID Type / Status
Subject US-ARCOM E676779 entity
Predicate commendationType P166166 FINISHED
Object commendation medal 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: commendation medal | Statement: [US-ARCOM, commendationType, commendation medal]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: commendationType
Context triple: [US-ARCOM, commendationType, commendation medal]
  • A. recommendation
    Indicates that one entity suggests, endorses, or advises another entity as suitable or beneficial for a particular purpose or context.
  • B. recommendationProcess
    Indicates the process by which one entity evaluates options and suggests a preferred choice or course of action to another entity.
  • C. recommendationHorizon
    Indicates the time span into the future for which a recommendation or forecast is intended to remain relevant or valid.
  • D. canRecommend
    Indicates that one entity is able or authorized to suggest or endorse another entity as suitable or preferable.
  • E. recommendedIn
    Indicates that one entity is suggested or endorsed within the context, content, or scope of another entity (such as a document, list, or recommendation source).
  • F. None of above. chosen

Provenance (4 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_69eee9bb44988190b6e11652d028bc59 completed April 27, 2026, 4:44 a.m.
NER Named-entity recognition batch_69f66003a3f48190a2ba6da5aafbb5cb completed May 2, 2026, 8:35 p.m.
PD Predicate disambiguation batch_69f65c1f94ac8190bc6fbc7916fc0d82 completed May 2, 2026, 8:18 p.m.
PDg Predicate description generation batch_69f65f75ac608190a62cd6afce14f68e completed May 2, 2026, 8:32 p.m.
Created at: April 27, 2026, 5:36 a.m.