Triple

T19940840
Position Surface form Disambiguated ID Type / Status
Subject Latona E479302 entity
Predicate hasMyth P43504 FINISHED
Object Niobe myth 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: Niobe myth | Statement: [Latona, hasMyth, Niobe myth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Niobe myth
Context triple: [Latona, hasMyth, Niobe myth]
  • A. Niobe chosen
    Niobe is a figure in Greek mythology whose tragic story centers on her pride in her many children and the devastating divine retribution that followed.
  • B. Niobe in Rome
    Niobe in Rome is a character from the historical drama television series "Rome," portrayed as a complex and long-suffering wife navigating the political and personal turmoil of late Republican Rome.
  • C. Antiope
    Antiope is an Amazonian queen in Greek mythology, often associated with Athens through her relationship with the hero Theseus.
  • D. Antiope
    Antiope is a figure in Greek mythology, often associated with Thebes and known for her tragic story involving Zeus and the birth of the twins Amphion and Zethus.
  • E. Aphrodite's vengeance
    Aphrodite's vengeance is the divine retribution of the Greek goddess of love, whose wrath drives tragic passions and destructive fates in mythological figures such as Phaedra.
  • 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_69d8e522a17c819095165d4d24939fd8 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65a1a8df4819094e84855465df6c0 completed April 20, 2026, 4:53 p.m.
Created at: April 10, 2026, 1:54 p.m.