Triple

T16649501
Position Surface form Disambiguated ID Type / Status
Subject Marcella De Marchis E404564 entity
Predicate name P16 FINISHED
Object Marcella De Marchis E404564 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: Marcella De Marchis | Statement: [Marcella De Marchis, name, Marcella De Marchis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marcella De Marchis
Context triple: [Marcella De Marchis, name, Marcella De Marchis]
  • A. Marcella De Marchis chosen
    Marcella De Marchis was an Italian costume and production designer active in mid-20th-century cinema and theater.
  • B. Claudia de Matteis
    Claudia de Matteis is known as the former wife of American real estate broker and film producer Raphael De Niro, son of actor Robert De Niro.
  • C. Irene Morra
    Irene Morra is a scholar and editor known for her work on literature and culture, including editing the volume "Road to Morocco."
  • D. Irene Morra
    Irene Morra was a film editor known for her work on early 20th-century American cinema, including the Shirley Temple film "The Little Colonel."
  • E. Maura Del Serra
    Maura Del Serra is an Italian writer and playwright known for her contributions to contemporary Italian literature and theater.
  • 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_69d8838a41f08190b0c3f79c47df5078 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37ad85ec881909dc6a434a363dab1 completed April 18, 2026, 12:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00aaeaf4388190aa5340a01938b3f2 completed May 10, 2026, 3:57 p.m.
Created at: April 10, 2026, 5:18 a.m.