Triple

T22366652
Position Surface form Disambiguated ID Type / Status
Subject 13 Minutes E552921 entity
Predicate productionCompany P490 FINISHED
Object Broth Film
Broth Film is a film production company known for producing the historical drama thriller "13 Minutes."
E1532310 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: Broth Film | Statement: [13 Minutes, productionCompany, Broth Film]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Broth Film
Context triple: [13 Minutes, productionCompany, Broth Film]
  • A. Film Begets Film
    Film Begets Film is a critical study by film historian Jay Leyda that examines the influence of existing films on the creation and evolution of new cinematic works.
  • B. The Bro
    The Bro is a high-thrill water slide attraction at WhiteWater World, known for its fast, twisting ride experience.
  • C. Thura Film
    Thura Film is a Danish film production company known for producing the 1994 horror-thriller "Nightwatch."
  • D. Robis Film
    Robis Film is a film production company best known for producing the acclaimed Egyptian drama "The Night of Counting the Years."
  • E. Chungeorahm Film
    Chungeorahm Film is a South Korean film production company best known internationally for producing Bong Joon-ho’s monster movie "The Host."
  • 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: Broth Film
Triple: [13 Minutes, productionCompany, Broth Film]
Generated description
Broth Film is a film production company known for producing the historical drama thriller "13 Minutes."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Broth Film
Target entity description: Broth Film is a film production company known for producing the historical drama thriller "13 Minutes."
  • A. Film Begets Film
    Film Begets Film is a critical study by film historian Jay Leyda that examines the influence of existing films on the creation and evolution of new cinematic works.
  • B. The Bro
    The Bro is a high-thrill water slide attraction at WhiteWater World, known for its fast, twisting ride experience.
  • C. Thura Film
    Thura Film is a Danish film production company known for producing the 1994 horror-thriller "Nightwatch."
  • D. Robis Film
    Robis Film is a film production company best known for producing the acclaimed Egyptian drama "The Night of Counting the Years."
  • E. Chungeorahm Film
    Chungeorahm Film is a South Korean film production company best known internationally for producing Bong Joon-ho’s monster movie "The Host."
  • 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_69e11e4affcc8190ba7c27d29062558d completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1580074dc819091305ac7017000d3 completed April 29, 2026, 12:59 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ae065f01481909ddf2c27e2b471bf completed May 18, 2026, 9:48 a.m.
NEDg Description generation batch_6a0ae16a8bcc8190852dd17f9c780123 completed May 18, 2026, 9:52 a.m.
NED2 Entity disambiguation (via description) batch_6a0ae1e16fac8190b0b56d00a87d173f completed May 18, 2026, 9:54 a.m.
Created at: April 16, 2026, 8:44 p.m.