Triple

T30980358
Position Surface form Disambiguated ID Type / Status
Subject Village Urugwiro E789354 entity
Predicate servesAs P268 FINISHED
Object office of the President of Rwanda
The office of the President of Rwanda is the executive institution responsible for the country's head of state and government, overseeing national policy, governance, and representation at both domestic and international levels.
E1940670 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: office of the President of Rwanda | Statement: [Village Urugwiro, servesAs, office of the President of Rwanda]
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: office of the President of Rwanda
Triple: [Village Urugwiro, servesAs, office of the President of Rwanda]
Generated description
The office of the President of Rwanda is the executive institution responsible for the country's head of state and government, overseeing national policy, governance, and representation at both domestic and international levels.

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_69f224c4831c8190be53924ec25a150a completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f693bdb5e48190a30cff40f057ee6c completed May 3, 2026, 12:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a28fbc18a3c8190abb011a9eba5beee completed June 10, 2026, 5:53 a.m.
NEDg Description generation batch_6a28ffc3037481909e380c0b60ebce5c completed June 10, 2026, 6:10 a.m.
NED2 Entity disambiguation (via description) batch_6a29005bb6bc81909fa20caeb92ac2be completed June 10, 2026, 6:12 a.m.
Created at: April 29, 2026, 8:55 p.m.