Triple

T5091205
Position Surface form Disambiguated ID Type / Status
Subject Human Rights Watch E114754 entity
Predicate hasKeyPerson P256 FINISHED
Object Tirana Hassan
Tirana Hassan is a human rights lawyer and advocate who serves as the executive director of Human Rights Watch, leading global efforts to investigate and expose human rights abuses.
 E492524 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: Tirana Hassan | Statement: [Human Rights Watch, hasKeyPerson, Tirana Hassan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tirana Hassan
Context triple: [Human Rights Watch, hasKeyPerson, Tirana Hassan]
  • A. Shabana
    Shabana is a prominent Bangladeshi film actress renowned for her extensive and influential career in Bengali cinema.
  • B. Salma
    Salma is a feminine given name of Arabic origin, commonly used in various cultures around the world.
  • C. Mizzi Ahmar
    Mizzi Ahmar is a reddish variety of Jerusalem stone commonly used as a traditional building material in and around Jerusalem.
  • D. Riza Aziz
    Riza Aziz is a Malaysian film producer and co-founder of Red Granite Pictures, known for financing high-profile Hollywood films and being embroiled in the 1MDB corruption scandal.
  • E. Anna Kashfi
    Anna Kashfi was a British-Indian actress and the first wife of Hollywood star Marlon Brando.
  • 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: Tirana Hassan
Triple: [Human Rights Watch, hasKeyPerson, Tirana Hassan]
Generated description
Tirana Hassan is a human rights lawyer and advocate who serves as the executive director of Human Rights Watch, leading global efforts to investigate and expose human rights abuses.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tirana Hassan
Target entity description: Tirana Hassan is a human rights lawyer and advocate who serves as the executive director of Human Rights Watch, leading global efforts to investigate and expose human rights abuses.
  • A. Shabana
    Shabana is a prominent Bangladeshi film actress renowned for her extensive and influential career in Bengali cinema.
  • B. Salma
    Salma is a feminine given name of Arabic origin, commonly used in various cultures around the world.
  • C. Mizzi Ahmar
    Mizzi Ahmar is a reddish variety of Jerusalem stone commonly used as a traditional building material in and around Jerusalem.
  • D. Riza Aziz
    Riza Aziz is a Malaysian film producer and co-founder of Red Granite Pictures, known for financing high-profile Hollywood films and being embroiled in the 1MDB corruption scandal.
  • E. Anna Kashfi
    Anna Kashfi was a British-Indian actress and the first wife of Hollywood star Marlon Brando.
  • 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_69bd443e941881908eb4e8c685b6f656 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7541b2bc8190b58c2a23733b7825 completed March 20, 2026, 4:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69beb14d1ea88190b8bc523ff44478f6 completed March 21, 2026, 2:55 p.m.
NEDg Description generation batch_69beb252ca2c8190b1bf7978b50c7ef6 completed March 21, 2026, 2:59 p.m.
NED2 Entity disambiguation (via description) batch_69beb2b989788190b81e6f60398bd49d completed March 21, 2026, 3:01 p.m.
Created at: March 20, 2026, 1:40 p.m.