Triple

T4943866
Position Surface form Disambiguated ID Type / Status
Subject Dido E110999 entity
Predicate nameVariant P744 FINISHED
Object Elissa E121100 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: Elissa | Statement: [Dido, nameVariant, Elissa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elissa
Context triple: [Dido, nameVariant, Elissa]
  • A. Elissa chosen
    Elissa, also known as Dido, is the legendary Phoenician princess who founded the ancient city of Carthage and became its first queen.
  • B. Elissa Leonard
    Elissa Leonard is an American filmmaker and producer known for her work in documentary and independent film, as well as for being married to Federal Reserve Chair Jerome H. Powell.
  • C. Mya
    Mya is a central female character in the romantic comedy film "Think Like a Man," known for following Steve Harvey’s dating advice as she navigates modern relationships.
  • D. Elissa Knight
    Elissa Knight is an American voice actress best known for voicing the character EVE in Pixar's animated film "WALL-E."
  • E. Lorelei Ambrosia
    Lorelei Ambrosia is a glamorous, comedic antagonist and accomplice to the villain Ross Webster in the 1983 superhero film Superman III.
  • 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_69bd441721cc819085c7e33fe0876818 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd70a7650c8190b046b65072fd8eae completed March 20, 2026, 4:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69be77c6566c8190b0c76c05b9d82053 completed March 21, 2026, 10:49 a.m.
Created at: March 20, 2026, 1:31 p.m.