Triple

T23274746
Position Surface form Disambiguated ID Type / Status
Subject Lake E588386 entity
Predicate hasNotableBearer P458 FINISHED
Object Ricki Lake NE NERFINISHED

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: Ricki Lake | Statement: [Lake, hasNotableBearer, Ricki Lake]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ricki Lake
Context triple: [Lake, hasNotableBearer, Ricki Lake]
  • A. Rickie Lake chosen
    Ricki Lake is an American actress and television host best known for her role in the film "Hairspray" and for hosting the long-running daytime talk show "Ricki Lake."
  • B. Ricki Tarr
    Ricki Tarr is a British intelligence operative and key informant in John le Carré’s espionage novel "Tinker Tailor Soldier Spy," whose actions help uncover a high-level Soviet mole.
  • C. Karrine Steffans
    Karrine Steffans is an American author and former video vixen best known for her bestselling memoirs about her experiences in the hip-hop industry.
  • D. Krystal Keith
    Krystal Keith is an American country music singer and songwriter, and the daughter of country star Toby Keith.
  • E. Bridgette Wilson
    Bridgette Wilson is an American actress, singer, and former Miss Teen USA best known for her roles in 1990s films such as "Billy Madison" and "Mortal Kombat."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e25d148adc819088efbf42672604e9 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f195768b1c8190ae7cbf8c316ae4dd completed April 29, 2026, 5:21 a.m.
Created at: April 17, 2026, 4:47 p.m.