Triple

T18237068
Position Surface form Disambiguated ID Type / Status
Subject GiveWell E436708 entity
Predicate hasDonationsDirected P130360 FINISHED
Object hundreds of millions of US dollars LITERAL FINISHED

How this triple was built (2 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: hundreds of millions of US dollars | Statement: [GiveWell, hasDonationsDirected, hundreds of millions of US dollars]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasDonationsDirected
Context triple: [GiveWell, hasDonationsDirected, hundreds of millions of US dollars]
  • A. donatedWith
    Indicates that an entity made a donation using, accompanied by, or in association with a particular method, item, or context.
  • B. donatedToState
    Indicates that an entity has given or transferred something, such as money, goods, or assets, as a donation to a state or state-level governmental body.
  • C. donated
    Indicates that one entity voluntarily gave something of value (such as money, goods, or time) to another entity, typically without expecting anything in return.
  • D. hasDonorFocus
    Indicates that an entity is oriented toward, tailored to, or primarily concerned with the interests, needs, or priorities of donors.
  • E. typeOfDonations
    Indicates the kinds or categories of donations involved in a given context or transaction.
  • F. None of above. chosen

Provenance (4 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.
PD Predicate disambiguation batch_69e4332336cc8190808b9c70c888ba65 completed April 19, 2026, 1:42 a.m.
PDg Predicate description generation batch_69e438f684e48190b38c64b58c518b6a completed April 19, 2026, 2:07 a.m.
Created at: April 10, 2026, 10:33 a.m.