Triple

T19027101
Position Surface form Disambiguated ID Type / Status
Subject Blocket AB E465636 entity
Predicate brandName P1500 FINISHED
Object Blocket 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: Blocket | Statement: [Blocket AB, brandName, Blocket]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Blocket
Context triple: [Blocket AB, brandName, Blocket]
  • A. Blocket chosen
    Blocket is a major Swedish online classifieds marketplace for buying and selling goods and services, owned by the media group Schibsted.
  • B. Bazaar
    Bazaar is a distributed version control system designed for ease of use and flexible workflows, commonly used for managing source code and collaborative software development.
  • C. Bazaar
    Bazaar is a 1982 Hindi-language drama film that critically portrays the social and emotional consequences of arranged marriages driven by dowry and economic pressures in Indian society.
  • D. The Bucket
    "The Bucket" is a song by American rock band Kings of Leon, known for its catchy guitar riffs and reflective lyrics about the pressures of early fame.
  • E. Rhypes
    Rhypes was an ancient Greek city in Achaea, traditionally known as the hometown of the mythic founder Myskellos.
  • 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_69d8dd0359648190bc2a9202c5cf29d2 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d73dc404819092059e496662d151 completed April 20, 2026, 7:35 a.m.
Created at: April 10, 2026, 12:02 p.m.