Triple

T14327946
Position Surface form Disambiguated ID Type / Status
Subject Laura Montez E355260 entity
Predicate portrayedBy P1507 FINISHED
Object Andrea Savage E1056829 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: Andrea Savage | Statement: [Laura Montez, portrayedBy, Andrea Savage]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrea Savage
Context triple: [Laura Montez, portrayedBy, Andrea Savage]
  • A. Andrea Savage chosen
    Andrea Savage is an American actress, comedian, and writer known for her work in film and television comedies, including creating and starring in the series "I'm Sorry."
  • B. Andrea Leeds
    Andrea Leeds was an American film actress best known for her acclaimed performances in 1930s Hollywood, including an Oscar-nominated role in "Stage Door."
  • C. Andrea McArdle
    Andrea McArdle is an American actress and singer best known for originating the title role in the Broadway musical "Annie."
  • D. Andrea Cornish
    Andrea Cornish is a pivotal murder victim whose mysterious death drives the central investigation and plot of the HBO crime drama miniseries "The Night Of."
  • E. Andrea Warren
    Andrea Warren is a film and animation producer known for her work on major animated features at Pixar Animation Studios.
  • 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_69d8278fa2108190bc0d0e7939c1eb03 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8c1c3e70819084b6728ac5c18561 completed April 14, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdd5be63848190aa71f009ceaea1b3 completed May 8, 2026, 12:23 p.m.
Created at: April 10, 2026, 1:13 a.m.