Triple

T17961676
Position Surface form Disambiguated ID Type / Status
Subject Dr. Kananga E449097 entity
Predicate employs P7 FINISHED
Object Whisper
Whisper is a henchman and assassin in the James Bond film "Live and Let Die," known for working under the villain Dr. Kananga.
 E1298958 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: Whisper | Statement: [Dr. Kananga, employs, Whisper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Whisper
Context triple: [Dr. Kananga, employs, Whisper]
  • A. Whisper
    Whisper is an open-source automatic speech recognition system by OpenAI that transcribes and translates spoken language with high accuracy across many languages.
  • B. Whisper
    Whisper is a feminine hygiene brand of sanitary napkins and related products owned by Procter & Gamble and sold in various international markets.
  • C. Whisper
    Whisper is a 2007 supernatural horror film in which a botched kidnapping leads to terrifying events surrounding a mysterious young boy.
  • D. Whispering
    "Whispering" is a popular early 20th-century American popular song and jazz standard that has been widely recorded and adapted by numerous artists.
  • E. Whispers
    Whispers is a musical artist known for collaborating with Styles David on the project "Ghost Your Enthusiasm."
  • 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: Whisper
Triple: [Dr. Kananga, employs, Whisper]
Generated description
Whisper is a henchman and assassin in the James Bond film "Live and Let Die," known for working under the villain Dr. Kananga.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Whisper
Target entity description: Whisper is a henchman and assassin in the James Bond film "Live and Let Die," known for working under the villain Dr. Kananga.
  • A. Whisper
    Whisper is an open-source automatic speech recognition system by OpenAI that transcribes and translates spoken language with high accuracy across many languages.
  • B. Whisper
    Whisper is a feminine hygiene brand of sanitary napkins and related products owned by Procter & Gamble and sold in various international markets.
  • C. Whisper
    Whisper is a 2007 supernatural horror film in which a botched kidnapping leads to terrifying events surrounding a mysterious young boy.
  • D. Whispering
    "Whispering" is a popular early 20th-century American popular song and jazz standard that has been widely recorded and adapted by numerous artists.
  • E. Whispers
    Whispers is a musical artist known for collaborating with Styles David on the project "Ghost Your Enthusiasm."
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4b132cc10819088526a0b4b098d69 completed April 19, 2026, 10:40 a.m.
NED1 Entity disambiguation (via context triple) batch_6a03300dae988190ab1b9f0e40e96fe5 completed May 12, 2026, 1:50 p.m.
NEDg Description generation batch_6a03310fd4608190b8c23df661ddc2ad completed May 12, 2026, 1:54 p.m.
NED2 Entity disambiguation (via description) batch_6a03330f373c81908bb2418dfbeec74f completed May 12, 2026, 2:02 p.m.
Created at: April 10, 2026, 10:22 a.m.