Triple

T4212630
Position Surface form Disambiguated ID Type / Status
Subject Isaias Afwerki E93940 entity
Predicate familyName P18 FINISHED
Object Afwerki
Afwerki is the surname of Isaias Afwerki, the long-serving president and founding leader of Eritrea.
E421988 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: Afwerki | Statement: [Isaias Afwerki, familyName, Afwerki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Afwerki
Context triple: [Isaias Afwerki, familyName, Afwerki]
  • A. Labori
    Labori was a prominent French defense lawyer best known for representing Alfred Dreyfus during the politically charged Dreyfus affair.
  • B. Laborec
    Laborec is a river in eastern Slovakia that flows through the Carpathian region and is a tributary of the Latorica River.
  • C. Vueltabajo
    Vueltabajo is a renowned tobacco-growing region in western Cuba, famous for producing some of the world’s finest cigar tobacco.
  • D. HaAvoda
    HaAvoda is the Hebrew name and common abbreviation for the Israeli Labor Party, a major social-democratic political party in Israel.
  • E. Laborem exercens
    Laborem exercens is a 1981 social encyclical by Pope John Paul II that reflects on the dignity of human work and the rights of workers in modern economic systems.
  • 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: Afwerki
Triple: [Isaias Afwerki, familyName, Afwerki]
Generated description
Afwerki is the surname of Isaias Afwerki, the long-serving president and founding leader of Eritrea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Afwerki
Target entity description: Afwerki is the surname of Isaias Afwerki, the long-serving president and founding leader of Eritrea.
  • A. Labori
    Labori was a prominent French defense lawyer best known for representing Alfred Dreyfus during the politically charged Dreyfus affair.
  • B. Laborec
    Laborec is a river in eastern Slovakia that flows through the Carpathian region and is a tributary of the Latorica River.
  • C. Vueltabajo
    Vueltabajo is a renowned tobacco-growing region in western Cuba, famous for producing some of the world’s finest cigar tobacco.
  • D. HaAvoda
    HaAvoda is the Hebrew name and common abbreviation for the Israeli Labor Party, a major social-democratic political party in Israel.
  • E. Laborem exercens
    Laborem exercens is a 1981 social encyclical by Pope John Paul II that reflects on the dignity of human work and the rights of workers in modern economic systems.
  • 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_69b3451743608190808f41d17ccf2650 completed March 12, 2026, 10:58 p.m.
NER Named-entity recognition batch_69b34be585848190b0b177b5516f53c1 completed March 12, 2026, 11:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69b59631e2cc8190b1d125b82a81593e completed March 14, 2026, 5:09 p.m.
NEDg Description generation batch_69b5970db8b48190b952d0fa08234f09 completed March 14, 2026, 5:12 p.m.
NED2 Entity disambiguation (via description) batch_69b59788ef308190a34c2f23f22a7e4d completed March 14, 2026, 5:14 p.m.
Created at: March 12, 2026, 11:04 p.m.