Triple

T6649137
Position Surface form Disambiguated ID Type / Status
Subject Existing Liabilities Scheme E150773 entity
Predicate isRetrospective P36523 FINISHED
Object true 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: true | Statement: [Existing Liabilities Scheme, isRetrospective, true]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isRetrospective
Context triple: [Existing Liabilities Scheme, isRetrospective, true]
  • A. isRetroactive chosen
    Indicates that an action, rule, or effect applies to a time period before its creation, enactment, or implementation.
  • B. isHistoric
    Indicates that something has significant importance or relevance in history, often due to its age, impact, or role in past events.
  • C. isRegressive
    Indicates that a process, change, or state moves backward or returns to a less advanced, less developed, or previously abandoned condition.
  • D. retrocededTo
    Indicates that control, ownership, or rights over something were returned or transferred back from one entity to another.
  • E. doesNotApplyRetroactivelyTo
    Indicates that a rule, law, or condition does not affect events, actions, or situations that occurred before it came into effect.
  • 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_69c687f1a3048190828b7342f7125d5c completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6cc9c6cb0819084fec8e0beb430de completed March 27, 2026, 6:29 p.m.
PD Predicate disambiguation batch_69c6ad04d66c8190926ffcbff372643b completed March 27, 2026, 4:15 p.m.
Created at: March 27, 2026, 2:01 p.m.