Triple

T10430176
Position Surface form Disambiguated ID Type / Status
Subject Opera Limited E245891 entity
Predicate product P490 FINISHED
Object Opera News E50831 NE 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: Opera News | Statement: [Opera Limited, product, Opera News]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Opera News
Context triple: [Opera Limited, product, Opera News]
  • A. Opera News chosen
    Opera News is a personalized news and content aggregation app focused on delivering trending stories, videos, and local updates, particularly popular in emerging markets.
  • B. Ruby Television
    Ruby Television is a television production company known for creating and developing screen content such as the series "Small Island."
  • C. Rubicon TV
    Rubicon TV is a Norwegian television production company known for creating scripted series such as the crime-comedy drama "Lilyhammer."
  • D. Acorn TV
    Acorn TV is a subscription streaming service specializing in British and international television dramas, mysteries, and comedies.
  • E. SVT Play
    SVT Play is Sweden’s national public service broadcaster’s online streaming platform, offering on-demand and live TV content.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d381bf3dc08190bf35a2643e4e8f22 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4ea62d6448190a7f5b785467824cf completed April 7, 2026, 11:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69d87eb068bc8190be9c7c916850278e completed April 10, 2026, 4:38 a.m.
Created at: April 6, 2026, 12:13 p.m.