Triple

T1062726
Position Surface form Disambiguated ID Type / Status
Subject Babes in Arms E22942 entity
Predicate castMember P1668 FINISHED
Object Rand Brooks
Rand Brooks was an American film and television actor best known for his roles in classic Hollywood productions such as "Gone with the Wind" and numerous Westerns.
 E134057 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: Rand Brooks | Statement: [Babes in Arms, castMember, Rand Brooks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rand Brooks
Context triple: [Babes in Arms, castMember, Rand Brooks]
  • A. Terry Brooks
    Terry Brooks is a bestselling American fantasy author best known for his long-running Shannara series.
  • B. Paul Darrow
    Paul Darrow was the son of famed American lawyer Clarence Darrow and a businessman who managed many of his father's financial affairs.
  • C. Dan Jewett
    Dan Jewett is an American science teacher known for his brief marriage to billionaire philanthropist and novelist MacKenzie Scott.
  • D. Alan Webber
    Alan Webber is an American politician and former business magazine co-founder who serves as the mayor of Santa Fe, New Mexico.
  • E. Charles Rackoff
    Charles Rackoff is a Canadian computer scientist known for his influential work in cryptography and computational complexity theory.
  • 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: Rand Brooks
Triple: [Babes in Arms, castMember, Rand Brooks]
Generated description
Rand Brooks was an American film and television actor best known for his roles in classic Hollywood productions such as "Gone with the Wind" and numerous Westerns.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rand Brooks
Target entity description: Rand Brooks was an American film and television actor best known for his roles in classic Hollywood productions such as "Gone with the Wind" and numerous Westerns.
  • A. Terry Brooks
    Terry Brooks is a bestselling American fantasy author best known for his long-running Shannara series.
  • B. Paul Darrow
    Paul Darrow was the son of famed American lawyer Clarence Darrow and a businessman who managed many of his father's financial affairs.
  • C. Dan Jewett
    Dan Jewett is an American science teacher known for his brief marriage to billionaire philanthropist and novelist MacKenzie Scott.
  • D. Alan Webber
    Alan Webber is an American politician and former business magazine co-founder who serves as the mayor of Santa Fe, New Mexico.
  • E. Charles Rackoff
    Charles Rackoff is a Canadian computer scientist known for his influential work in cryptography and computational complexity theory.
  • 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_69a493dada0481909c43649f9843ea91 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b8f68a54819084326d87c3498252 completed March 1, 2026, 10:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac66224db481909318add535721977 completed March 7, 2026, 5:53 p.m.
NEDg Description generation batch_69ac66d7aef881909f5bb83b4563c581 completed March 7, 2026, 5:56 p.m.
NED2 Entity disambiguation (via description) batch_69ac676cb9a08190a83d47de80126677 completed March 7, 2026, 5:59 p.m.
Created at: March 1, 2026, 7:42 p.m.