Triple

T4556149
Position Surface form Disambiguated ID Type / Status
Subject Maura Isles E120482 entity
Predicate portrayedBy P1507 FINISHED
Object Sasha Alexander E154621 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: Sasha Alexander | Statement: [Maura Isles, portrayedBy, Sasha Alexander]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sasha Alexander
Context triple: [Maura Isles, portrayedBy, Sasha Alexander]
  • A. Sasha Alexander chosen
    Sasha Alexander is an American actress best known for her television roles on series such as NCIS and Rizzoli & Isles.
  • B. Sasha Barrese
    Sasha Barrese is an American actress best known for playing Doug’s fiancée Tracy in the comedy film "The Hangover" and its sequels.
  • C. Alexandra Richards
    Alexandra Richards is an American model and artist, best known as the daughter of Rolling Stones guitarist Keith Richards and actress Patti Hansen.
  • D. Shana Alexander
    Shana Alexander was an American journalist and columnist best known for her incisive commentary and high-profile televised debates on the news program "60 Minutes."
  • E. Angelica Ross
    Angelica Ross is an American actress, producer, and transgender rights advocate best known for her groundbreaking roles in series like "Pose" and "American Horror Story."
  • 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_69bd4636f1648190a701445c2fcd9c17 completed March 20, 2026, 1:05 p.m.
NER Named-entity recognition batch_69bd5814f56c8190a65f61f6148b7e5a completed March 20, 2026, 2:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdc57d59f88190857cbda79caf3c38 completed March 20, 2026, 10:09 p.m.
Created at: March 20, 2026, 1:09 p.m.