Triple

T18905904
Position Surface form Disambiguated ID Type / Status
Subject Kohlberg Kravis Roberts & Co. E462461 entity
Predicate tickerSymbol P1447 FINISHED
Object KKR 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: KKR | Statement: [Kohlberg Kravis Roberts & Co., tickerSymbol, KKR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KKR
Context triple: [Kohlberg Kravis Roberts & Co., tickerSymbol, KKR]
  • A. KKR
    KKR is a popular franchise cricket team in the Indian Premier League based in Kolkata and co-owned by Bollywood actor Shah Rukh Khan.
  • B. KKR chosen
    KKR is a global investment firm best known as a pioneer in private equity and leveraged buyouts.
  • C. Kohlberg Kravis Roberts & Co.
    Kohlberg Kravis Roberts & Co. is a leading global private equity firm best known for pioneering large leveraged buyouts and shaping the modern buyout industry.
  • D. KPS Capital Partners
    KPS Capital Partners is a private equity firm known for acquiring and restructuring industrial and manufacturing businesses.
  • E. Roark Capital Group
    Roark Capital Group is a private equity firm known for investing in and building large multi-brand restaurant and consumer service companies.
  • 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_69d8dcfd05bc819088903cca13cc2846 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c52cc9cc8190ac489d36e51693c8 completed April 20, 2026, 6:18 a.m.
Created at: April 10, 2026, 11:58 a.m.