Triple

T19249359
Position Surface form Disambiguated ID Type / Status
Subject Salva Kiir Mayardit E481348 entity
Predicate givenName P17 FINISHED
Object Salva
Salva is the given name of Salva Kiir Mayardit, the longtime political leader and president of South Sudan.
 E1366474 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: Salva | Statement: [Salva Kiir Mayardit, givenName, Salva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Salva
Context triple: [Salva Kiir Mayardit, givenName, Salva]
  • A. Salva
    Salva is the alias used by the mastermind character known as The Professor in the Spanish heist television series "Money Heist" (La Casa de Papel).
  • B. Savea
    Savea is a Samoan-origin surname notably borne by New Zealand rugby union players such as brothers Julian and Ardie Savea.
  • C. SAVE
    SAVE is an Italian company, formally known as SAVE S.p.A., primarily involved in the management and development of airport infrastructure and related services.
  • D. SAVE
    SAVE is the stock ticker symbol for Spirit Airlines, a U.S.-based ultra-low-cost carrier known for its no-frills service model.
  • E. Save
    The Save is a river in southwestern France that flows through the Occitanie region before joining the Garonne.
  • 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: Salva
Triple: [Salva Kiir Mayardit, givenName, Salva]
Generated description
Salva is the given name of Salva Kiir Mayardit, the longtime political leader and president of South Sudan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Salva
Target entity description: Salva is the given name of Salva Kiir Mayardit, the longtime political leader and president of South Sudan.
  • A. Salva
    Salva is the alias used by the mastermind character known as The Professor in the Spanish heist television series "Money Heist" (La Casa de Papel).
  • B. Savea
    Savea is a Samoan-origin surname notably borne by New Zealand rugby union players such as brothers Julian and Ardie Savea.
  • C. SAVE
    SAVE is the stock ticker symbol for Spirit Airlines, a U.S.-based ultra-low-cost carrier known for its no-frills service model.
  • D. SAVE
    SAVE is an Italian company, formally known as SAVE S.p.A., primarily involved in the management and development of airport infrastructure and related services.
  • E. Save
    The Save is a river in southwestern France that flows through the Occitanie region before joining the Garonne.
  • 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_69d8e8cd9d1081908a181d02b88b59b8 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fb2f43e48190abab5257bec8e6aa completed April 20, 2026, 10:08 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0705e2d3948190b1ff731f648f68c7 completed May 15, 2026, 11:39 a.m.
NEDg Description generation batch_6a0706bd92b48190848fcf5be679d207 completed May 15, 2026, 11:42 a.m.
NED2 Entity disambiguation (via description) batch_6a070763ca5c81908afa73b30645223a completed May 15, 2026, 11:45 a.m.
Created at: April 10, 2026, 1:27 p.m.