Triple

T5168358
Position Surface form Disambiguated ID Type / Status
Subject Soraya Esfandiary-Bakhtiary E116613 entity
Predicate mother P120 FINISHED
Object Eva Karl
Eva Karl was the German mother of Soraya Esfandiary-Bakhtiary, the former Queen consort of Iran and second wife of Shah Mohammad Reza Pahlavi.
E499618 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: Eva Karl | Statement: [Soraya Esfandiary-Bakhtiary, mother, Eva Karl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eva Karl
Context triple: [Soraya Esfandiary-Bakhtiary, mother, Eva Karl]
  • A. Eva Wagner
    Eva Wagner was a daughter of the famed German composer Richard Wagner, belonging to the prominent Wagner family closely associated with the Bayreuth Festival.
  • B. Eva Schubach
    Eva Schubach is known as a former spouse of Gerhard Schröder, the one-time Chancellor of Germany.
  • C. Eva Huber
    Eva Huber is a notable individual who shares the surname Huber, recognized enough to be specifically cited as a bearer of the name.
  • D. Eva Dahlgren
    Eva Dahlgren is a Swedish pop and rock singer-songwriter known for her introspective lyrics and influential role in Scandinavian music since the late 1970s.
  • E. Marlene Knaus
    Marlene Knaus is an Austrian former model best known as the ex-wife of Formula One legend Niki Lauda.
  • 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: Eva Karl
Triple: [Soraya Esfandiary-Bakhtiary, mother, Eva Karl]
Generated description
Eva Karl was the German mother of Soraya Esfandiary-Bakhtiary, the former Queen consort of Iran and second wife of Shah Mohammad Reza Pahlavi.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Eva Karl
Target entity description: Eva Karl was the German mother of Soraya Esfandiary-Bakhtiary, the former Queen consort of Iran and second wife of Shah Mohammad Reza Pahlavi.
  • A. Eva Wagner
    Eva Wagner was a daughter of the famed German composer Richard Wagner, belonging to the prominent Wagner family closely associated with the Bayreuth Festival.
  • B. Eva Schubach
    Eva Schubach is known as a former spouse of Gerhard Schröder, the one-time Chancellor of Germany.
  • C. Eva Huber
    Eva Huber is a notable individual who shares the surname Huber, recognized enough to be specifically cited as a bearer of the name.
  • D. Eva Dahlgren
    Eva Dahlgren is a Swedish pop and rock singer-songwriter known for her introspective lyrics and influential role in Scandinavian music since the late 1970s.
  • E. Marlene Knaus
    Marlene Knaus is an Austrian former model best known as the ex-wife of Formula One legend Niki Lauda.
  • 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_69bd445ff97c81909a2615cc56235470 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd794b87508190be3b82726ef4b37c completed March 20, 2026, 4:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69bed93f33ac8190b2f60a8e95685bc8 completed March 21, 2026, 5:45 p.m.
NEDg Description generation batch_69beda0419108190862d028a14227e8a completed March 21, 2026, 5:48 p.m.
NED2 Entity disambiguation (via description) batch_69bedaa232ac81908c5ee2d4ba8cbcd7 completed March 21, 2026, 5:51 p.m.
Created at: March 20, 2026, 1:45 p.m.