Triple

T18237062
Position Surface form Disambiguated ID Type / Status
Subject GiveWell E436708 entity
Predicate recommends P488 FINISHED
Object Helen Keller International NE NERFINISHED

How this triple was built (3 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: Helen Keller International | Statement: [GiveWell, recommends, Helen Keller International]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Helen Keller International
Context triple: [GiveWell, recommends, Helen Keller International]
  • A. World Childhood Foundation
    The World Childhood Foundation is an international non-profit organization dedicated to protecting children from violence, exploitation, and sexual abuse, co-founded by Queen Silvia of Sweden.
  • B. Save the Children
    Save the Children is an international non-governmental organization that works to improve the lives, health, education, and protection of children worldwide.
  • C. Caritas Internationalis
    Caritas Internationalis is a global confederation of Catholic charitable organizations dedicated to humanitarian aid, social justice, and development work in over 200 countries and territories.
  • D. Women for Women International
    Women for Women International is a global nonprofit organization that supports women survivors of war and conflict through social and economic empowerment programs.
  • E. The Sanneh Foundation
    The Sanneh Foundation is a nonprofit organization focused on empowering youth and promoting community development through educational, athletic, and social programs.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Helen Keller International
Target entity description: Helen Keller International is a global nonprofit organization focused on preventing blindness and reducing malnutrition through evidence-based health and nutrition programs in low-income countries.
  • A. World Childhood Foundation
    The World Childhood Foundation is an international non-profit organization dedicated to protecting children from violence, exploitation, and sexual abuse, co-founded by Queen Silvia of Sweden.
  • B. Save the Children
    Save the Children is an international non-governmental organization that works to improve the lives, health, education, and protection of children worldwide.
  • C. Caritas Internationalis
    Caritas Internationalis is a global confederation of Catholic charitable organizations dedicated to humanitarian aid, social justice, and development work in over 200 countries and territories.
  • D. Women for Women International
    Women for Women International is a global nonprofit organization that supports women survivors of war and conflict through social and economic empowerment programs.
  • E. The Sanneh Foundation
    The Sanneh Foundation is a nonprofit organization focused on empowering youth and promoting community development through educational, athletic, and social programs.
  • F. None of above. chosen

Provenance (2 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_69d8b91104e08190a8241f7d260a5162 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4f7def3c48190a9a96c8b4911f0f3 completed April 19, 2026, 3:42 p.m.
Created at: April 10, 2026, 10:33 a.m.