Triple

T15506542
Position Surface form Disambiguated ID Type / Status
Subject Sam Levenson E379095 entity
Predicate spouse P13 FINISHED
Object Esther Levine
Esther Levine was the wife of American humorist and television host Sam Levenson.
E1193377 NE FINISHED

How this triple was built (4 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: Esther Levine | Statement: [Sam Levenson, spouse, Esther Levine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Esther Levine
Context triple: [Sam Levenson, spouse, Esther Levine]
  • A. Esther Roisman
    Esther Roisman was the wife of renowned American investigative journalist and independent publisher I.F. Stone.
  • B. Esther Blau
    Esther Blau is known as the mother of author and Wiccan priestess Deborah Blake.
  • C. Esther Bubley
    Esther Bubley was an American documentary photographer best known for her intimate, human-centered images of everyday life in mid-20th-century America, particularly during and after World War II.
  • D. Esther Ross
    Esther Ross was the woman who served as the sponsor and ceremonial namesake figure for the U.S. Navy battleship USS Arizona (BB-39) at its christening.
  • E. Esther Shapiro
    Esther Shapiro is an American television writer and producer best known for co-creating the hit 1980s prime-time soap opera "Dynasty."
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Esther Levine
Triple: [Sam Levenson, spouse, Esther Levine]
Generated description
Esther Levine was the wife of American humorist and television host Sam Levenson.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Esther Levine
Target entity description: Esther Levine was the wife of American humorist and television host Sam Levenson.
  • A. Esther Roisman
    Esther Roisman was the wife of renowned American investigative journalist and independent publisher I.F. Stone.
  • B. Esther Blau
    Esther Blau is known as the mother of author and Wiccan priestess Deborah Blake.
  • C. Esther Bubley
    Esther Bubley was an American documentary photographer best known for her intimate, human-centered images of everyday life in mid-20th-century America, particularly during and after World War II.
  • D. Esther Ross
    Esther Ross was the woman who served as the sponsor and ceremonial namesake figure for the U.S. Navy battleship USS Arizona (BB-39) at its christening.
  • E. Esther Shapiro
    Esther Shapiro is an American television writer and producer best known for co-creating the hit 1980s prime-time soap opera "Dynasty."
  • F. None of above. chosen

Provenance (5 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_69d85cd53a7c819080f5b9042c4c199e completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03fcea8888190a7b69aca360183c3 completed April 16, 2026, 1:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe46436048190b79d1d18a179617b completed May 10, 2026, 1:50 a.m.
NEDg Description generation batch_69ffe5ced2dc8190922b910d1a6c08d3 completed May 10, 2026, 1:56 a.m.
NED2 Entity disambiguation (via description) batch_69ffe687c204819092a4a8de0b9d624d completed May 10, 2026, 1:59 a.m.
Created at: April 10, 2026, 3:55 a.m.