Triple

T7662812
Position Surface form Disambiguated ID Type / Status
Subject Joe Slovo E173548 entity
Predicate spouse P13 FINISHED
Object Helena Dolny
Helena Dolny is a South African academic, author, and former head of the Land Bank, known for her work in land reform and social justice.
 E680048 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: Helena Dolny | Statement: [Joe Slovo, spouse, Helena Dolny]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Helena Dolny
Context triple: [Joe Slovo, spouse, Helena Dolny]
  • A. Husinec
    Husinec is a small Czech town best known as the birthplace of the religious reformer Jan Hus.
  • B. Svatava
    Svatava is a river in Central Europe that flows through parts of Germany and the Czech Republic before joining the Ohře River.
  • C. Beránek
    Beránek is a Czech surname and word meaning "little lamb," commonly used as a family name in Czech-speaking regions.
  • D. Dôle
    Dôle is a traditional Swiss red wine blend from the Valais region, typically made from Pinot Noir and Gamay grapes and known for its fruity, approachable character.
  • E. Kriváň
    Kriváň is a prominent and symbolically important peak in Slovakia’s High Tatras, often regarded as a national symbol and popular hiking destination.
  • 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: Helena Dolny
Triple: [Joe Slovo, spouse, Helena Dolny]
Generated description
Helena Dolny is a South African academic, author, and former head of the Land Bank, known for her work in land reform and social justice.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Helena Dolny
Target entity description: Helena Dolny is a South African academic, author, and former head of the Land Bank, known for her work in land reform and social justice.
  • A. Husinec
    Husinec is a small Czech town best known as the birthplace of the religious reformer Jan Hus.
  • B. Svatava
    Svatava is a river in Central Europe that flows through parts of Germany and the Czech Republic before joining the Ohře River.
  • C. Beránek
    Beránek is a Czech surname and word meaning "little lamb," commonly used as a family name in Czech-speaking regions.
  • D. Dôle
    Dôle is a traditional Swiss red wine blend from the Valais region, typically made from Pinot Noir and Gamay grapes and known for its fruity, approachable character.
  • E. Kriváň
    Kriváň is a prominent and symbolically important peak in Slovakia’s High Tatras, often regarded as a national symbol and popular hiking destination.
  • 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_69c69955517c819085bc715b96d304d2 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c701a74a2c81909f78ab2de7ce807c completed March 27, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c89b1aaef081908d1d181ea7c28c2f completed March 29, 2026, 3:23 a.m.
NEDg Description generation batch_69c89e177fd08190a6f3a70cf32365d9 completed March 29, 2026, 3:35 a.m.
NED2 Entity disambiguation (via description) batch_69c89e7328f4819088651b60e7af457d completed March 29, 2026, 3:37 a.m.
Created at: March 27, 2026, 3:59 p.m.