Triple

T12644098
Position Surface form Disambiguated ID Type / Status
Subject Bilal Erdoğan E301974 entity
Predicate sibling P363 FINISHED
Object Sümeyye Erdoğan Bayraktar E49331 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: Sümeyye Erdoğan Bayraktar | Statement: [Bilal Erdoğan, sibling, Sümeyye Erdoğan Bayraktar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sümeyye Erdoğan Bayraktar
Context triple: [Bilal Erdoğan, sibling, Sümeyye Erdoğan Bayraktar]
  • A. Sümeyye Erdoğan chosen
    Sümeyye Erdoğan is a Turkish political figure and activist, best known as the daughter of President Recep Tayyip Erdoğan and for her involvement in social and charitable initiatives.
  • B. Sema Erdoğan
    Sema Erdoğan is known as the wife of Ahmet Burak Erdoğan, the son of Turkish President Recep Tayyip Erdoğan.
  • C. Aslı Erdoğan
    Aslı Erdoğan is a Turkish writer, human rights activist, and former physicist known for her politically charged novels and essays that critique state violence and oppression.
  • D. Esra Erdoğan
    Esra Erdoğan is the daughter of Turkish President Recep Tayyip Erdoğan and a public figure involved in educational and social initiatives in Turkey.
  • E. Emine Erdoğan
    Emine Erdoğan is the First Lady of Turkey, known for her social and humanitarian initiatives, particularly in education, women's empowerment, and refugee support.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d7bdec9f9c8190b4bac675b7588211 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9614bf2f881909976becdf747f4fb completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6719a45d881908dd895836a225781 completed May 2, 2026, 9:50 p.m.
Created at: April 9, 2026, 5:17 p.m.