Triple

T18195885
Position Surface form Disambiguated ID Type / Status
Subject Ilithyia E435659 entity
Predicate sibling P363 FINISHED
Object Hebe 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: Hebe | Statement: [Ilithyia, sibling, Hebe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hebe
Context triple: [Ilithyia, sibling, Hebe]
  • A. Hebe chosen
    Hebe is the Greek goddess of youth, traditionally known as the cupbearer of the gods on Mount Olympus.
  • B. Melina
    Melina is a key resistance fighter and love interest in the science fiction film "Total Recall," known for aiding the protagonist in his struggle against a corrupt Martian regime.
  • C. Alessandra
    Alessandra is an Italian politician, former actress, and granddaughter of Benito Mussolini.
  • D. Alessandra
    Alessandra is an Italian given name, the feminine form of Alessandro, equivalent to Alexandra in English.
  • E. Aya
    Aya is a Mesopotamian goddess primarily known as the consort of the sun god Shamash and associated with dawn and light.
  • 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_69d8b90dba6481908e119eb9aa4ca0cb completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e0d2ad5881909d846f3851ac9ec9 completed April 19, 2026, 2:04 p.m.
Created at: April 10, 2026, 10:31 a.m.