Triple

T19217708
Position Surface form Disambiguated ID Type / Status
Subject Fidelidade E480528 entity
Predicate hasSubsidiary P254 FINISHED
Object OK! Teleseguros 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: OK! Teleseguros | Statement: [Fidelidade, hasSubsidiary, OK! Teleseguros]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OK! Teleseguros
Context triple: [Fidelidade, hasSubsidiary, OK! Teleseguros]
  • A. OK! Teleseguros chosen
    OK! Teleseguros is a Portuguese insurance brand specializing in direct, often online-based insurance services.
  • B. Metrópolis Seguros
    Metrópolis Seguros is a Spanish insurance company best known for owning the iconic Edificio Metrópolis in Madrid.
  • C. Esurance
    Esurance is a U.S.-based online-focused auto and home insurance company known for its direct-to-consumer model and digital tools for buying and managing policies.
  • D. שירות הביטחון הכללי
    שירות הביטחון הכללי הוא ארגון הביטחון הפנימי והמודיעין של מדינת ישראל, האחראי על סיכול טרור, ריגול ואיומים ביטחוניים בתוך המדינה.
  • E. TD Insurance
    TD Insurance is a Canadian insurance provider offering products such as home, auto, life, and travel coverage as part of the Toronto-Dominion Bank (TD) group.
  • 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_69d8e8cb8c348190b52075823911c869 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fa3c552c8190b22844e5b7adfc50 completed April 20, 2026, 10:04 a.m.
Created at: April 10, 2026, 1:23 p.m.