Triple

T16785748
Position Surface form Disambiguated ID Type / Status
Subject The Green Goddess E407967 entity
Predicate character P662 FINISHED
Object Lucilla Crespin E421510 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: Lucilla Crespin | Statement: [The Green Goddess, character, Lucilla Crespin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lucilla Crespin
Context triple: [The Green Goddess, character, Lucilla Crespin]
  • A. Lucilla Crespin chosen
    Lucilla Crespin is a fictional character featured in the 1923 silent drama film "The Green Goddess."
  • B. Luisa Cortés
    Luisa Cortés is a figure known primarily for her association with Julio Zapata, about whom limited public biographical information is available.
  • C. Matilde Andrades
    Matilde Andrades was the mother of influential American artist Jean-Michel Basquiat.
  • D. Gladys Serra
    Gladys Serra was the mother of American minimalist sculptor Richard Serra.
  • E. Rosa Loy
    Rosa Loy is a contemporary German painter associated with the New Leipzig School, known for her enigmatic, dreamlike figurative works that often explore female perspectives and surreal narratives.
  • 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_69d8839270588190886720d9519bbf8f completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b21a52ac8190b4374aa0fc45683a completed April 18, 2026, 4:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00cfc0dcd081909f715e0f2aad67c7 completed May 10, 2026, 6:34 p.m.
Created at: April 10, 2026, 5:22 a.m.