Triple

T23317543
Position Surface form Disambiguated ID Type / Status
Subject Albert "Mister" Johnson E590750 entity
Predicate marriedTo P13 FINISHED
Object Celie 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: Celie | Statement: [Albert "Mister" Johnson, marriedTo, Celie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Celie
Context triple: [Albert "Mister" Johnson, marriedTo, Celie]
  • A. Celie Johnson chosen
    Celie Johnson is the resilient, abused African-American woman at the center of Alice Walker’s novel and its film adaptation "The Color Purple," portrayed on screen by Whoopi Goldberg.
  • B. Janie
    Janie is a feminine given name commonly used as a diminutive form of Jane.
  • C. Cora
    Cora is an indigenous Uto-Aztecan language spoken primarily by the Cora people in the Sierra del Nayar region of western Mexico.
  • D. Cora
    Cora is the American-born Countess of Grantham in the British television series "Downton Abbey," known for her compassionate nature and role as matriarch of the Crawley family.
  • E. Cora
    Cora was an ancient town of Latium in central Italy, historically associated with the Latin League and later integrated into the Roman sphere.
  • 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_69e25d1d32188190948eb76909d1dcc3 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f197828c408190ae071624e40de4cc completed April 29, 2026, 5:30 a.m.
Created at: April 17, 2026, 5:06 p.m.