Triple

T14447960
Position Surface form Disambiguated ID Type / Status
Subject Brave Search E358254 entity
Predicate accessibleVia P1985 FINISHED
Object search.brave.com E358254 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: search.brave.com | Statement: [Brave Search, accessibleVia, search.brave.com]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: search.brave.com
Context triple: [Brave Search, accessibleVia, search.brave.com]
  • A. OpenSearch
    OpenSearch is an open-source, community-driven search and analytics engine and suite derived from Elasticsearch, used for full-text search, log analytics, and observability at scale.
  • B. Brave Search chosen
    Brave Search is a privacy-focused, independent search engine developed by Brave that emphasizes user anonymity and reduced tracking.
  • C. Qwant
    Qwant is a French privacy-focused search engine that emphasizes user anonymity and does not track or profile its users.
  • D. DuckDuckGo
    DuckDuckGo is a privacy-focused internet search engine that emphasizes not tracking users or personalizing search results based on their data.
  • E. Internet search
    Internet search is the process of using specialized software and algorithms to locate relevant information across the World Wide Web based on user queries.
  • 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_69d82794dfa081909b9134ad2e32244b completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de9160126c8190a2862a1a3dde1aff completed April 14, 2026, 7:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6d86dbc0819085fef8fa8b45b373 completed May 8, 2026, 4:58 a.m.
Created at: April 10, 2026, 1:19 a.m.