Triple

T9724952
Position Surface form Disambiguated ID Type / Status
Subject Esther Smith E235584 entity
Predicate givenName P17 FINISHED
Object Esther E20171 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: Esther | Statement: [Esther Smith, givenName, Esther]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Esther
Context triple: [Esther Smith, givenName, Esther]
  • A. Esther chosen
    Esther is a book of the Hebrew Bible and Christian Old Testament that tells the story of a Jewish woman who becomes queen of Persia and courageously saves her people from annihilation.
  • B. Esther
    Esther is a central character in Paulo Coelho’s novel *The Zahir*, portrayed as the missing wife whose disappearance drives the narrator’s obsessive spiritual and emotional quest.
  • C. Esther and the King
    Esther and the King is a 1960 biblical epic film dramatizing the Old Testament story of Queen Esther and her efforts to save the Jewish people in ancient Persia.
  • D. Vashti
    Vashti is a central character in E.M. Forster’s dystopian science fiction story "The Machine Stops," embodying blind faith in a technologically controlled, isolated society.
  • E. Vashti
    Vashti is the deposed queen of Persia in the biblical Book of Esther, known for refusing King Ahasuerus’s command to appear before his guests.
  • 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_69ca84d0fad481909cdd45aa77416c48 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9e7838448190a7b5b259765a0d95 completed April 1, 2026, 10:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19fadc2948190b405fb7f249b82aa completed April 4, 2026, 11:33 p.m.
Created at: March 30, 2026, 8:21 p.m.