Triple

T27181823
Position Surface form Disambiguated ID Type / Status
Subject Ramphele E683213 entity
Predicate positionHeld P8 FINISHED
Object Managing Director at the World Bank
The Managing Director at the World Bank is a top-level executive responsible for overseeing the institution’s global operations, strategic initiatives, and policy implementation to advance international development and reduce poverty.
E1761650 NE 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: Managing Director at the World Bank | Statement: [Ramphele, positionHeld, Managing Director at the World Bank]
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: Managing Director at the World Bank
Triple: [Ramphele, positionHeld, Managing Director at the World Bank]
Generated description
The Managing Director at the World Bank is a top-level executive responsible for overseeing the institution’s global operations, strategic initiatives, and policy implementation to advance international development and reduce poverty.

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_69eefad140408190b8586fdebcf9af46 completed April 27, 2026, 5:57 a.m.
NER Named-entity recognition batch_69f6257dbc80819085041feaec6387b3 completed May 2, 2026, 4:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12538e8e208190816f0de6cf5cf2d4 completed May 24, 2026, 1:25 a.m.
NEDg Description generation batch_6a1254e770288190994c682cfe0f8c9d completed May 24, 2026, 1:31 a.m.
NED2 Entity disambiguation (via description) batch_6a12558ffcd08190b9a167ead908e052 completed May 24, 2026, 1:34 a.m.
Created at: April 27, 2026, 9:28 a.m.