Triple

T9101523
Position Surface form Disambiguated ID Type / Status
Subject Na dne E218168 entity
Predicate titleInRussian P23454 FINISHED
Object На дне E218169 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: На дне | Statement: [Na dne, titleInRussian, На дне]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: На дне
Context triple: [Na dne, titleInRussian, На дне]
  • A. На дне chosen
    «На дне» — социально-психологическая драма Максима Горького о жизни обитателей ночлежки, ставшая классикой русской литературы и театра.
  • B. Down in the Depths
    "Down in the Depths" is a classic Cole Porter torch song, best known through jazz and pop vocal interpretations such as Ella Fitzgerald’s.
  • C. Passages of the Deep
    Passages of the Deep is an immersive underwater tunnel exhibit that allows visitors to walk through large marine habitats and observe sharks, rays, and other ocean life up close.
  • D. The Dive
    The Dive is a science fiction film produced by James Cameron’s Lightstorm Entertainment, known for its deep-sea adventure and cutting-edge underwater visual effects.
  • E. Down to a Soundless Sea
    Down to a Soundless Sea is a collection of short stories by Thom Steinbeck that explores the lives and struggles of people along California’s Central Coast.
  • 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_69ca83d9844081908e561e367fda6d45 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc971435d08190b5007ed44ac0a364 completed April 1, 2026, 3:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0182d8ea08190b4337a77b47019a5 completed April 3, 2026, 7:42 p.m.
Created at: March 30, 2026, 7:15 p.m.