Triple

T19197478
Position Surface form Disambiguated ID Type / Status
Subject The Customs Union Issue E470008 entity
Predicate regardsAsImportant P1887 FINISHED
Object pattern of trade flows after integration 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: pattern of trade flows after integration | Statement: [The Customs Union Issue, regardsAsImportant, pattern of trade flows after integration]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: regardsAsImportant
Context triple: [The Customs Union Issue, regardsAsImportant, pattern of trade flows after integration]
  • A. isImportantFor chosen
    Indicates that something holds significant value, relevance, or necessity in relation to something else.
  • B. resultImportance
    Indicates that one entity specifies how significant, critical, or impactful the outcome or result of another entity is.
  • C. peakImportance
    Indicates that something reaches or represents the highest level of importance within a given context or timeframe.
  • D. importanceInEvent
    Indicates the degree to which an entity plays a significant or central role within a particular event.
  • E. importantSaint
    Indicates that the subject is recognized as a particularly significant or highly revered saint within a religious or spiritual tradition.
  • 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_69d8dd0ad9088190a173b32657ae2e7a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f8a695cc8190b84a220f52c51dfc completed April 20, 2026, 9:57 a.m.
PD Predicate disambiguation batch_69e4b9bb158481909478ca2e06f3ba39 completed April 19, 2026, 11:17 a.m.
Created at: April 10, 2026, 12:07 p.m.