Triple

T10102187
Position Surface form Disambiguated ID Type / Status
Subject Hunyadi family E216228 entity
Predicate notableMember P10 FINISHED
Object Michael Szilágyi
Michael Szilágyi was a 15th-century Hungarian nobleman and military leader, best known as the uncle and supporter of King Matthias Corvinus.
 E861236 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: Michael Szilágyi | Statement: [Hunyadi family, notableMember, Michael Szilágyi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Michael Szilágyi
Context triple: [Hunyadi family, notableMember, Michael Szilágyi]
  • A. Laszlo Halasz
    Laszlo Halasz was a Hungarian-American conductor and opera director best known as the founding director of the New York City Opera.
  • B. Zoltán Nagy
    Zoltán Nagy is a Hungarian name shared by several notable individuals, including professionals in fields such as sports, music, and academia.
  • C. András Nagy
    András Nagy is a Hungarian biologist and stem cell researcher known for his pioneering work in embryonic stem cells and regenerative medicine.
  • D. Andras Hamori
    Andras Hamori is a film producer known for his work on various international and independent movies.
  • E. Zoltán Szilvássy
    Zoltán Szilvássy is a Hungarian physician and academic who has served as rector of the University of Debrecen.
  • 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: Michael Szilágyi
Triple: [Hunyadi family, notableMember, Michael Szilágyi]
Generated description
Michael Szilágyi was a 15th-century Hungarian nobleman and military leader, best known as the uncle and supporter of King Matthias Corvinus.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Michael Szilágyi
Target entity description: Michael Szilágyi was a 15th-century Hungarian nobleman and military leader, best known as the uncle and supporter of King Matthias Corvinus.
  • A. Laszlo Halasz
    Laszlo Halasz was a Hungarian-American conductor and opera director best known as the founding director of the New York City Opera.
  • B. Zoltán Nagy
    Zoltán Nagy is a Hungarian name shared by several notable individuals, including professionals in fields such as sports, music, and academia.
  • C. András Nagy
    András Nagy is a Hungarian biologist and stem cell researcher known for his pioneering work in embryonic stem cells and regenerative medicine.
  • D. Andras Hamori
    Andras Hamori is a film producer known for his work on various international and independent movies.
  • E. Zoltán Szilvássy
    Zoltán Szilvássy is a Hungarian physician and academic who has served as rector of the University of Debrecen.
  • 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_69ca83d039f08190b9d10363221c69fb completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cdd099c21c819097aac4f0f168a2da completed April 2, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7fb12ac9c819087a182c12653792c completed April 9, 2026, 7:16 p.m.
NEDg Description generation batch_69d822d303888190aa556287b3b1cc03 completed April 9, 2026, 10:06 p.m.
NED2 Entity disambiguation (via description) batch_69d859b05a3881908c97cb173d160e44 completed April 10, 2026, 2 a.m.
Created at: March 30, 2026, 9:02 p.m.