Triple

T17892647
Position Surface form Disambiguated ID Type / Status
Subject Türkiye İş Bankası E447359 entity
Predicate shortName P43 FINISHED
Object İşbank NE NERFINISHED

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: İşbank | Statement: [Türkiye İş Bankası, shortName, İşbank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: İşbank
Context triple: [Türkiye İş Bankası, shortName, İşbank]
  • A. Ziraat Bankası
    Ziraat Bankası is one of Turkey’s largest and oldest state-owned banks, widely recognized for its extensive retail and corporate banking services and prominent sports sponsorships.
  • B. Türkiye İş Bankası chosen
    Türkiye İş Bankası is one of Turkey’s largest and oldest commercial banks, playing a central role in the country’s modern financial system and economic development.
  • C. QNB Finansbank
    QNB Finansbank is a major Turkish bank offering a wide range of retail and corporate banking services as part of the Qatar National Bank Group.
  • D. Gosbank
    Gosbank was the central bank of the Soviet Union, responsible for issuing currency and overseeing the state-controlled financial system.
  • E. Takasbank
    Takasbank is Turkey’s central clearing and settlement institution, providing post-trade, custody, and risk management services for the country’s capital markets.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49d7a855c8190b20bdbf6dcd4fd47 completed April 19, 2026, 9:16 a.m.
Created at: April 10, 2026, 10:19 a.m.