Triple

T22560707
Position Surface form Disambiguated ID Type / Status
Subject Mary Ellen Walton E557806 entity
Predicate givenName P17 FINISHED
Object Mary Ellen 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: Mary Ellen | Statement: [Mary Ellen Walton, givenName, Mary Ellen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Ellen
Context triple: [Mary Ellen Walton, givenName, Mary Ellen]
  • A. Mary Ellen chosen
    Mary Ellen is a feminine given name of English origin, often used as a compound of "Mary" and "Ellen."
  • B. Mary Clare
    Mary Clare was a British stage and film actress known for her character roles in early 20th-century cinema and theatre.
  • C. Ellen Mangles
    Ellen Mangles was the wife of Scottish naval officer and colonial governor Sir James Stirling, noted as a prominent figure in early Western Australian colonial society.
  • D. Mary Ellen Lancaster
    Mary Ellen Lancaster was the mother of the infamous American bank robber John Dillinger.
  • E. Mary Ellen Henderson
    Mary Ellen Henderson was an educator and civil rights advocate whose legacy in promoting equal educational opportunities led to a middle school being named in her honor.
  • 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_69e11e59db848190b4272ecd2b690ffd completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15fa5f4008190921095b7aff4f4e2 completed April 29, 2026, 1:32 a.m.
Created at: April 16, 2026, 8:52 p.m.