Triple
T27466183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viktor Orbán |
E693182
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Anikó Lévai
Anikó Lévai is a Hungarian lawyer and author best known as the longtime wife of Prime Minister Viktor Orbán and for her work in social and charitable causes.
|
E1774933
|
NE FINISHED |
How this triple was built (2 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: Anikó Lévai | Statement: [Viktor Orbán, spouse, Anikó Lévai]
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: Anikó Lévai Triple: [Viktor Orbán, spouse, Anikó Lévai]
Generated description
Anikó Lévai is a Hungarian lawyer and author best known as the longtime wife of Prime Minister Viktor Orbán and for her work in social and charitable causes.
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_69ef538105548190a771cc5a0cf8c211 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62dfd746481908fead735f9ccd021 |
completed | May 2, 2026, 5:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a12bbdee4888190a2cc72407ad6cb56 |
completed | May 24, 2026, 8:50 a.m. |
| NEDg | Description generation | batch_6a12bc906eb481908d12f171b1230dbe |
completed | May 24, 2026, 8:53 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a12bd38f1948190a0b1f05ff28d8289 |
completed | May 24, 2026, 8:56 a.m. |
Created at: April 27, 2026, 12:52 p.m.