Triple

T14521133
Position Surface form Disambiguated ID Type / Status
Subject May December E340652 entity
Predicate producer P490 FINISHED
Object Jessica Elbaum E1118667 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: Jessica Elbaum | Statement: [May December, producer, Jessica Elbaum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jessica Elbaum
Context triple: [May December, producer, Jessica Elbaum]
  • A. Jessica Elbaum chosen
    Jessica Elbaum is a film producer known for her work on acclaimed comedies, including the coming-of-age film "Booksmart," and for collaborating frequently with Will Ferrell and Adam McKay’s production ventures.
  • B. Danielle Judovits
    Danielle Judovits is an American voice actress known for her work in animated television series and video games.
  • C. Julia Feldman
    Julia Feldman is a character in the television series "NCIS: Los Angeles," known primarily as a relative of Special Agent Kensi Blye.
  • D. Jessica Hershberg
    Jessica Hershberg is an American stage actress and singer known for her work in musical theatre and as the wife of actor Santino Fontana.
  • E. Alina Margolis
    Alina Margolis was a Polish Jewish pediatrician, Holocaust survivor, and humanitarian activist known for her medical and social work, including with organizations aiding Jews during and after World War II.
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de9a72cff08190878b4bed9b0b5eb5 completed April 14, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe729f894881908647da558bef1031 completed May 8, 2026, 11:32 p.m.
Created at: April 10, 2026, 1:22 a.m.