Triple

T742453
Position Surface form Disambiguated ID Type / Status
Subject Herod the Great E15271 entity
Predicate child P120 FINISHED
Object Salome E66081 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: Salome | Statement: [Herod the Great, child, Salome]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Salome
Context triple: [Herod the Great, child, Salome]
  • A. Salome chosen
    Salome is a biblical and historical figure best known for her dance before Herod Antipas that led to the beheading of John the Baptist.
  • B. La Goulue
    La Goulue was the stage name of Louise Weber, a famous late-19th-century French can-can dancer at the Moulin Rouge and a popular subject of Toulouse-Lautrec’s posters.
  • C. MAMACITA
    "MAMACITA" is a 2020 Latin-influenced pop and reggaeton single by the Black Eyed Peas featuring Ozuna and J. Rey Soul.
  • D. Madam
    "Madam" is a formal term of address for a woman, often used to show respect or politeness in social, professional, or official contexts.
  • E. Judith
    Judith is a deuterocanonical book of the Bible that tells the story of a courageous Jewish widow who saves her people by beheading the Assyrian general Holofernes.
  • 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_69a49358aa308190adbc9b5a0a2adcf9 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a60e286c81908787a41cf9b9f150 completed March 1, 2026, 8:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69a64a63f9288190b86e4a75467acce0 completed March 3, 2026, 2:41 a.m.
Created at: March 1, 2026, 7:37 p.m.