Triple

T11666353
Position Surface form Disambiguated ID Type / Status
Subject Red Buttons E277259 entity
Predicate spouse P13 FINISHED
Object Roxanne Arlen
Roxanne Arlen was an American film and television actress active in the 1950s and 1960s, known for her supporting roles in Hollywood productions.
E951810 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: Roxanne Arlen | Statement: [Red Buttons, spouse, Roxanne Arlen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roxanne Arlen
Context triple: [Red Buttons, spouse, Roxanne Arlen]
  • A. Alice Arlen
    Alice Arlen was an American screenwriter best known for co-writing acclaimed films such as "Silkwood" and "Alamo Bay."
  • B. Helen Merrill
    Helen Merrill is an American jazz vocalist renowned for her cool, introspective style and influential recordings with leading jazz musicians of the 1950s.
  • C. Phyllis Calvert
    Phyllis Calvert was a prominent British film and stage actress, best known as one of the leading stars of 1940s British cinema.
  • D. Mabel Mercer
    Mabel Mercer was a renowned British-born cabaret singer celebrated for her subtle, conversational style and influential interpretations of the Great American Songbook.
  • E. Crystal Langhorne
    Crystal Langhorne is an American former professional basketball player and WNBA All-Star known for her efficient post play and key contributions to multiple championship-contending teams.
  • 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: Roxanne Arlen
Triple: [Red Buttons, spouse, Roxanne Arlen]
Generated description
Roxanne Arlen was an American film and television actress active in the 1950s and 1960s, known for her supporting roles in Hollywood productions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Roxanne Arlen
Target entity description: Roxanne Arlen was an American film and television actress active in the 1950s and 1960s, known for her supporting roles in Hollywood productions.
  • A. Alice Arlen
    Alice Arlen was an American screenwriter best known for co-writing acclaimed films such as "Silkwood" and "Alamo Bay."
  • B. Helen Merrill
    Helen Merrill is an American jazz vocalist renowned for her cool, introspective style and influential recordings with leading jazz musicians of the 1950s.
  • C. Phyllis Calvert
    Phyllis Calvert was a prominent British film and stage actress, best known as one of the leading stars of 1940s British cinema.
  • D. Mabel Mercer
    Mabel Mercer was a renowned British-born cabaret singer celebrated for her subtle, conversational style and influential interpretations of the Great American Songbook.
  • E. Crystal Langhorne
    Crystal Langhorne is an American former professional basketball player and WNBA All-Star known for her efficient post play and key contributions to multiple championship-contending teams.
  • 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_69d6aafd0a448190b44da30af8c6c519 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a43f438081909da476294a057c38 completed April 10, 2026, 7:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69f280acab488190b1a912dc0e82bc44 completed April 29, 2026, 10:05 p.m.
NEDg Description generation batch_69f2b8b73f28819089ac252f7f823efb completed April 30, 2026, 2:04 a.m.
NED2 Entity disambiguation (via description) batch_69f2c4120f448190ac0ac944e77cb20e completed April 30, 2026, 2:53 a.m.
Created at: April 8, 2026, 9:39 p.m.