Triple

T19094829
Position Surface form Disambiguated ID Type / Status
Subject Regulations annexed to ADN E467378 entity
Predicate harmonizedWith P435 FINISHED
Object ADR NE NERFINISHED

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: ADR | Statement: [Regulations annexed to ADN, harmonizedWith, ADR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ADR
Context triple: [Regulations annexed to ADN, harmonizedWith, ADR]
  • A. ADR
    ADR is the commonly used abbreviation for the Azerbaijan Democratic Republic, the first secular democratic republic in the Muslim world established in 1918.
  • B. ADR
    ADR is the ICAO airline designator assigned to the former Slovenian national carrier Adria Airways.
  • C. ADR chosen
    ADR is a European treaty that sets harmonized rules and safety standards for the international transport of dangerous goods by road.
  • D. AAD
    AAD is the currency abbreviation for the Arab Accounting Dinar, a unit of account used by the Arab Monetary Fund.
  • E. ARD
    ARD is Germany’s main public broadcasting consortium, operating a network of regional broadcasters that together provide national radio, television, and online services.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dd05ac4c8190b1967d8f97f3fb2f completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e34e1ee0819092f679d916e6e532 completed April 20, 2026, 8:26 a.m.
Created at: April 10, 2026, 12:04 p.m.