Triple

T15747206
Position Surface form Disambiguated ID Type / Status
Subject László Tőkés E381749 entity
Predicate familyName P18 FINISHED
Object Tőkés
Tőkés is the Hungarian family name of László Tőkés, a prominent ethnic Hungarian Reformed pastor and politician from Romania known for his role in the events leading to the 1989 Romanian Revolution.
 E1173942 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: Tőkés | Statement: [László Tőkés, familyName, Tőkés]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tőkés
Context triple: [László Tőkés, familyName, Tőkés]
  • A. Töhötöm
    Töhötöm is a legendary chieftain of the early Hungarian tribes, traditionally counted among the leaders who guided the Magyars into the Carpathian Basin.
  • B. Törst
    Törst is a 1976 rock album by Swedish singer-songwriter Ulf Lundell, regarded as one of his early defining releases.
  • C. Tookes
    Tookes is the surname of American fashion model Jasmine Tookes, known for her work with Victoria’s Secret.
  • D. Toker
    Toker is a variant form of the given name or surname Tucker, used as an alternative spelling or derivative.
  • E. Zifta
    Zifta is a city in Egypt’s Nile Delta region known for its agricultural surroundings and location within the Gharbia Governorate.
  • 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: Tőkés
Triple: [László Tőkés, familyName, Tőkés]
Generated description
Tőkés is the Hungarian family name of László Tőkés, a prominent ethnic Hungarian Reformed pastor and politician from Romania known for his role in the events leading to the 1989 Romanian Revolution.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tőkés
Target entity description: Tőkés is the Hungarian family name of László Tőkés, a prominent ethnic Hungarian Reformed pastor and politician from Romania known for his role in the events leading to the 1989 Romanian Revolution.
  • A. Töhötöm
    Töhötöm is a legendary chieftain of the early Hungarian tribes, traditionally counted among the leaders who guided the Magyars into the Carpathian Basin.
  • B. Törst
    Törst is a 1976 rock album by Swedish singer-songwriter Ulf Lundell, regarded as one of his early defining releases.
  • C. Tookes
    Tookes is the surname of American fashion model Jasmine Tookes, known for her work with Victoria’s Secret.
  • D. Toker
    Toker is a variant form of the given name or surname Tucker, used as an alternative spelling or derivative.
  • E. Zifta
    Zifta is a city in Egypt’s Nile Delta region known for its agricultural surroundings and location within the Gharbia Governorate.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0502d72008190b4d13a6b3a12e467 completed April 16, 2026, 2:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff8309cba881909579ee5a62b3aa31 completed May 9, 2026, 6:55 p.m.
NEDg Description generation batch_69ff83d929a48190aea75597b864d210 completed May 9, 2026, 6:58 p.m.
NED2 Entity disambiguation (via description) batch_69ff8469354c819080b8cfddb7c66be5 completed May 9, 2026, 7 p.m.
Created at: April 10, 2026, 4:46 a.m.