Triple

T13415670
Position Surface form Disambiguated ID Type / Status
Subject Mary E313204 entity
Predicate follows P134 FINISHED
Object Sarkology E304097 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: Sarkology | Statement: [Mary, follows, Sarkology]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarkology
Context triple: [Mary, follows, Sarkology]
  • A. Sarkology chosen
    Sarkology is a studio album by Ghanaian rapper Sarkodie that showcases his blend of hip hop and Afrobeats and helped solidify his status in African music.
  • B. End of the World Museum
    End of the World Museum is a regional history museum in Ushuaia, Argentina, showcasing the natural, cultural, and maritime heritage of Tierra del Fuego and the southernmost regions of the world.
  • C. Stone Zoo
    Stone Zoo is a medium-sized zoological park in Stoneham, Massachusetts, featuring a variety of animal exhibits and family-oriented educational programs.
  • D. Panoptikum wax museum
    Panoptikum wax museum is a historic wax museum in Hamburg, Germany, known for its lifelike figures of celebrities, historical personalities, and cultural icons.
  • E. Whatizit
    Whatizit is a text-mining web service developed by the European Bioinformatics Institute for automatically identifying and annotating biological terms in scientific text.
  • 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_69d806ad0c44819088833ae1ec9e9690 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaeb6e904819098cc9153fd2feaf5 completed April 12, 2026, 2:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7308095548190afb659b84f2775f2 completed May 3, 2026, 11:24 a.m.
Created at: April 9, 2026, 9:39 p.m.