Triple

T18400820
Position Surface form Disambiguated ID Type / Status
Subject Rusalka (character) E449986 entity
Predicate parent P120 FINISHED
Object Vodník (Water Goblin) 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: Vodník (Water Goblin) | Statement: [Rusalka (character), parent, Vodník (Water Goblin)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vodník (Water Goblin)
Context triple: [Rusalka (character), parent, Vodník (Water Goblin)]
  • A. Goblin
    Goblin is the dark, experimental debut studio album by American rapper and producer Tyler, the Creator, known for its abrasive production and confessional, controversial lyrics.
  • B. Goblin
    Goblin is an Italian progressive rock band best known for its atmospheric, synth-driven soundtracks for horror films, particularly those of director Dario Argento.
  • C. Goblin
    Goblins in World of Warcraft are a cunning, profit-obsessed, and technologically inventive race known for their explosives, gadgets, and mercantile culture.
  • D. Vodyanoy chosen
    Vodyanoy is a malevolent water spirit from Slavic folklore, often depicted as an old, frog-like man who drowns people and guards rivers, ponds, and mills.
  • E. Gobrias
    Gobrias is a figure mentioned in ancient Near Eastern and classical sources, often associated with the Medo-Persian conquest of Babylon and the fall of King Belshazzar.
  • 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e5194f2a8c8190afcd7db23e3795fb completed April 19, 2026, 6:05 p.m.
Created at: April 10, 2026, 10:46 a.m.