Triple

T10530109
Position Surface form Disambiguated ID Type / Status
Subject Andrew G. Vajna E248416 entity
Predicate familyName P18 FINISHED
Object Vajna
Vajna is the surname of Andrew G. Vajna, a prominent Hungarian-American film producer known for co-founding Carolco Pictures and producing major action films such as the Rambo series.
 E869662 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: Vajna | Statement: [Andrew G. Vajna, familyName, Vajna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vajna
Context triple: [Andrew G. Vajna, familyName, Vajna]
  • A. Vajk
    Vajk was the original pagan name of Stephen I, the first Christian king and state-founder of Hungary.
  • B. Vlašim
    Vlašim is a small Czech town known for its historic château, English-style park, and location in the Central Bohemian Region southeast of Prague.
  • C. Ravanica
    Ravanica is a river in central Serbia that flows through the region before joining the Velika Morava.
  • D. Šavnik
    Šavnik is a small mountainous town and municipality in northern Montenegro, known for its rugged landscape and proximity to the Durmitor region.
  • E. Baška
    Baška is a popular coastal town and tourist resort on the island of Krk in Croatia, known for its long pebble beach and historic old town.
  • 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: Vajna
Triple: [Andrew G. Vajna, familyName, Vajna]
Generated description
Vajna is the surname of Andrew G. Vajna, a prominent Hungarian-American film producer known for co-founding Carolco Pictures and producing major action films such as the Rambo series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vajna
Target entity description: Vajna is the surname of Andrew G. Vajna, a prominent Hungarian-American film producer known for co-founding Carolco Pictures and producing major action films such as the Rambo series.
  • A. Vajk
    Vajk was the original pagan name of Stephen I, the first Christian king and state-founder of Hungary.
  • B. Vlašim
    Vlašim is a small Czech town known for its historic château, English-style park, and location in the Central Bohemian Region southeast of Prague.
  • C. Ravanica
    Ravanica is a river in central Serbia that flows through the region before joining the Velika Morava.
  • D. Šavnik
    Šavnik is a small mountainous town and municipality in northern Montenegro, known for its rugged landscape and proximity to the Durmitor region.
  • E. Baška
    Baška is a popular coastal town and tourist resort on the island of Krk in Croatia, known for its long pebble beach and historic old town.
  • 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_69d381c5c7448190bec34bee7ec72bac completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509f7d8ac8190b90c1a7f77b23545 completed April 7, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69d90e3caf4c8190b19199f1a68a00de completed April 10, 2026, 2:50 p.m.
NEDg Description generation batch_69d9107f488481908845aef0fdf6d60d completed April 10, 2026, 3 p.m.
NED2 Entity disambiguation (via description) batch_69d911790010819093fc50952502fd59 completed April 10, 2026, 3:04 p.m.
Created at: April 6, 2026, 12:30 p.m.