Triple

T12908819
Position Surface form Disambiguated ID Type / Status
Subject Jiří Hájek E308797 entity
Predicate familyName P18 FINISHED
Object Hájek
Hájek is a Czech surname borne by numerous notable figures in fields such as politics, science, and the arts.
 E1009149 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: Hájek | Statement: [Jiří Hájek, familyName, Hájek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hájek
Context triple: [Jiří Hájek, familyName, Hájek]
  • A. Hácha
    Hácha is a Czech surname most notably borne by Emil Hácha, the third President of Czechoslovakia who served during the early years of World War II.
  • B. Gabčík
    Gabčík is a Slovak surname most notably borne by Jozef Gabčík, a World War II resistance fighter involved in the assassination of Nazi official Reinhard Heydrich.
  • C. Kohout
    Kohout is a Czech surname borne by various notable individuals in fields such as literature, economics, and sports.
  • D. Dannhauser
    Dannhauser is a small town and local municipality in KwaZulu-Natal, South Africa, known historically for coal mining and agriculture.
  • E. Hufstedler
    Hufstedler is the surname of Shirley Hufstedler, a prominent American judge and the first U.S. Secretary of Education.
  • 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: Hájek
Triple: [Jiří Hájek, familyName, Hájek]
Generated description
Hájek is a Czech surname borne by numerous notable figures in fields such as politics, science, and the arts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hájek
Target entity description: Hájek is a Czech surname borne by numerous notable figures in fields such as politics, science, and the arts.
  • A. Hácha
    Hácha is a Czech surname most notably borne by Emil Hácha, the third President of Czechoslovakia who served during the early years of World War II.
  • B. Gabčík
    Gabčík is a Slovak surname most notably borne by Jozef Gabčík, a World War II resistance fighter involved in the assassination of Nazi official Reinhard Heydrich.
  • C. Kohout
    Kohout is a Czech surname borne by various notable individuals in fields such as literature, economics, and sports.
  • D. Dannhauser
    Dannhauser is a small town and local municipality in KwaZulu-Natal, South Africa, known historically for coal mining and agriculture.
  • E. Hufstedler
    Hufstedler is the surname of Shirley Hufstedler, a prominent American judge and the first U.S. Secretary of Education.
  • 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_69d7bdf92b588190acdf2a2291ac4590 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9719e584c81909be1ac1366effca0 completed April 10, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a5680d748190b8453793219bda8f completed May 3, 2026, 1:31 a.m.
NEDg Description generation batch_69f6a6f6b3348190b50560e747f78d62 completed May 3, 2026, 1:37 a.m.
NED2 Entity disambiguation (via description) batch_69f6a7c12ef8819095d2418d9999926a completed May 3, 2026, 1:41 a.m.
Created at: April 9, 2026, 5:41 p.m.