Triple

T6100913
Position Surface form Disambiguated ID Type / Status
Subject Carroll Ballard E135991 entity
Predicate notableWork P4 FINISHED
Object Duma
Duma is a 2005 family adventure film directed by Carroll Ballard about a boy and his close bond with an orphaned cheetah in South Africa.
 E569897 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: Duma | Statement: [Carroll Ballard, notableWork, Duma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Duma
Context triple: [Carroll Ballard, notableWork, Duma]
  • A. Barbusse
    Barbusse is the surname of Henri Barbusse, a French novelist and pacifist best known for his World War I novel "Le Feu" ("Under Fire").
  • B. Zyuzino
    Zyuzino is a Moscow Metro station on the Big Circle Line serving the Zyuzino District in southern Moscow.
  • C. Darrow
    Darrow is a surname most famously associated with Clarence Darrow, the prominent American lawyer and civil libertarian known for high-profile cases in the early 20th century.
  • D. Dalstroi
    Dalstroi was a Soviet state organization that managed forced labor camps and large-scale industrial and construction projects in the Kolyma region, particularly focused on gold mining.
  • E. Arapov
    Arapov is a Slavic masculine surname commonly found in Russian-speaking countries.
  • 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: Duma
Triple: [Carroll Ballard, notableWork, Duma]
Generated description
Duma is a 2005 family adventure film directed by Carroll Ballard about a boy and his close bond with an orphaned cheetah in South Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Duma
Target entity description: Duma is a 2005 family adventure film directed by Carroll Ballard about a boy and his close bond with an orphaned cheetah in South Africa.
  • A. Barbusse
    Barbusse is the surname of Henri Barbusse, a French novelist and pacifist best known for his World War I novel "Le Feu" ("Under Fire").
  • B. Zyuzino
    Zyuzino is a Moscow Metro station on the Big Circle Line serving the Zyuzino District in southern Moscow.
  • C. Darrow
    Darrow is a surname most famously associated with Clarence Darrow, the prominent American lawyer and civil libertarian known for high-profile cases in the early 20th century.
  • D. Dalstroi
    Dalstroi was a Soviet state organization that managed forced labor camps and large-scale industrial and construction projects in the Kolyma region, particularly focused on gold mining.
  • E. Arapov
    Arapov is a Slavic masculine surname commonly found in Russian-speaking countries.
  • 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_69c0087dee9881909e3655be88208c01 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c05b3aa9908190865be98ada141d37 completed March 22, 2026, 9:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1254b963081908e8e45968a7b29aa completed March 23, 2026, 11:34 a.m.
NEDg Description generation batch_69c129464108819086b1a3991ef4c9e1 completed March 23, 2026, 11:51 a.m.
NED2 Entity disambiguation (via description) batch_69c129d7cd348190963e1a266d5e88ae completed March 23, 2026, 11:53 a.m.
Created at: March 22, 2026, 4:13 p.m.