Triple

T16247509
Position Surface form Disambiguated ID Type / Status
Subject Schatze Page E394410 entity
Predicate hasFriend P8712 FINISHED
Object Pola Debevoise E394412 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: Pola Debevoise | Statement: [Schatze Page, hasFriend, Pola Debevoise]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pola Debevoise
Context triple: [Schatze Page, hasFriend, Pola Debevoise]
  • A. Pola Debevoise chosen
    Pola Debevoise is a glamorous, nearsighted fashion model portrayed by Marilyn Monroe in the 1953 romantic comedy film "How to Marry a Millionaire."
  • B. Craddock McDermott
    Craddock McDermott is the vengeful, malevolent ghost who serves as the primary antagonist in Joe Hill’s horror novel "Heart-Shaped Box."
  • C. Boies Penrose
    Boies Penrose was a powerful early 20th-century American Republican politician who served for decades as a U.S. Senator from Pennsylvania and was known as an influential party boss.
  • D. Sylvan Gotshal
    Sylvan Gotshal was an American lawyer and co-founder of the prominent international law firm Weil, Gotshal & Manges LLP.
  • E. Lawrence Weingarten
    Lawrence Weingarten was an American film producer best known for his work at MGM during Hollywood’s classic studio era, overseeing numerous popular comedies and dramas.
  • 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e245942460819080897afad0d2fe09 completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0017afc578819086478bbdddc149df completed May 10, 2026, 5:29 a.m.
Created at: April 10, 2026, 5:04 a.m.