Triple

T3110230
Position Surface form Disambiguated ID Type / Status
Subject Marlon Brando E64931 entity
Predicate spouse P13 FINISHED
Object Anna Kashfi
Anna Kashfi was a British-Indian actress and the first wife of Hollywood star Marlon Brando.
E332944 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: Anna Kashfi | Statement: [Marlon Brando, spouse, Anna Kashfi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anna Kashfi
Context triple: [Marlon Brando, spouse, Anna Kashfi]
  • A. Kinan Azmeh
    Kinan Azmeh is a Syrian clarinetist and composer known for blending classical, jazz, and Middle Eastern musical traditions in his performances and compositions.
  • B. Safia Farkash
    Safia Farkash is the second wife of former Libyan leader Muammar Gaddafi and the mother of several of his children, known primarily for her role as Libya’s de facto first lady during his rule.
  • C. Aida El-Kachef
    Aida El-Kachef is known as the wife of Egyptian diplomat and Nobel Peace Prize laureate Mohamed ElBaradei.
  • D. Hanan al-Shaykh
    Hanan al-Shaykh is a prominent Lebanese novelist and short story writer known for her bold explorations of gender, sexuality, and social norms in contemporary Arabic literature.
  • E. Hanan Hashim
    Hanan Hashim is the mother of Queen Alia al-Hussein of Jordan and a member of the extended Jordanian royal family.
  • 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: Anna Kashfi
Triple: [Marlon Brando, spouse, Anna Kashfi]
Generated description
Anna Kashfi was a British-Indian actress and the first wife of Hollywood star Marlon Brando.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Anna Kashfi
Target entity description: Anna Kashfi was a British-Indian actress and the first wife of Hollywood star Marlon Brando.
  • A. Kinan Azmeh
    Kinan Azmeh is a Syrian clarinetist and composer known for blending classical, jazz, and Middle Eastern musical traditions in his performances and compositions.
  • B. Safia Farkash
    Safia Farkash is the second wife of former Libyan leader Muammar Gaddafi and the mother of several of his children, known primarily for her role as Libya’s de facto first lady during his rule.
  • C. Aida El-Kachef
    Aida El-Kachef is known as the wife of Egyptian diplomat and Nobel Peace Prize laureate Mohamed ElBaradei.
  • D. Hanan al-Shaykh
    Hanan al-Shaykh is a prominent Lebanese novelist and short story writer known for her bold explorations of gender, sexuality, and social norms in contemporary Arabic literature.
  • E. Hanan Hashim
    Hanan Hashim is the mother of Queen Alia al-Hussein of Jordan and a member of the extended Jordanian royal family.
  • 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_69ad857eeaf48190b34ebfdaa7a264cf completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada437c5e08190af22f6fa11cf9252 completed March 8, 2026, 4:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b235a8949881908496a1413ffa2658 completed March 12, 2026, 3:40 a.m.
NEDg Description generation batch_69b236962ee48190b37836e5fe6dbc37 completed March 12, 2026, 3:44 a.m.
NED2 Entity disambiguation (via description) batch_69b237397e14819093a7192d28c59ad1 completed March 12, 2026, 3:47 a.m.
Created at: March 8, 2026, 3:04 p.m.