Triple

T11156857
Position Surface form Disambiguated ID Type / Status
Subject Erin Hannon E263931 entity
Predicate hasRelationshipWith P2830 FINISHED
Object Kelly Kapoor E223029 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: Kelly Kapoor | Statement: [Erin Hannon, hasRelationshipWith, Kelly Kapoor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kelly Kapoor
Context triple: [Erin Hannon, hasRelationshipWith, Kelly Kapoor]
  • A. Kelly Kapoor chosen
    Kelly Kapoor is a talkative, pop culture-obsessed customer service representative known for her dramatic personality and on-again, off-again relationship with Ryan Howard in the American version of The Office.
  • B. Karishma Kapoor
    Karishma Kapoor is a prominent Indian film actress from the Kapoor family, known for her leading roles in popular Bollywood movies of the 1990s and early 2000s.
  • C. Khushi Kapoor
    Khushi Kapoor is an Indian actress and model, best known as the younger daughter of legendary Bollywood star Sridevi and film producer Boney Kapoor.
  • D. Raha Kapoor
    Raha Kapoor is the daughter of prominent Bollywood actors Ranbir Kapoor and Alia Bhatt.
  • E. Ekta Kapoor
    Ekta Kapoor is a prominent Indian television and film producer known for revolutionizing Hindi soap operas and co-founding Balaji Telefilms.
  • 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_69d6aa9ccddc8190868998c8b7beb060 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8741cd48190b7cc29c6b6bc54ff completed April 9, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69e46352e0688190924f15bc7d7ede90 completed April 19, 2026, 5:08 a.m.
Created at: April 8, 2026, 9:28 p.m.