Triple

T12786163
Position Surface form Disambiguated ID Type / Status
Subject Ethel Skakel E305632 entity
Predicate hasChild P369 FINISHED
Object David Kennedy E338914 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: David Kennedy | Statement: [Ethel Skakel, hasChild, David Kennedy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Kennedy
Context triple: [Ethel Skakel, hasChild, David Kennedy]
  • A. David Kennedy chosen
    David Kennedy was a member of the prominent Kennedy family, known as one of Robert F. Kennedy’s sons and part of a major American political dynasty.
  • B. David Kennedy
    David Kennedy is a music producer known for his work on influential hip-hop projects such as Mos Def’s acclaimed album "Black on Both Sides."
  • C. David Kennedy
    David Kennedy is a prominent cybersecurity expert and penetration tester best known as the creator of the Social-Engineer Toolkit and founder of the security firm TrustedSec.
  • D. Tom Kennedy
    Tom Kennedy is an actor known for his role in the film "The Big House."
  • E. Christopher G. Kennedy
    Christopher G. Kennedy is an American businessman and member of the Kennedy political family, known for his work in real estate and public service in Illinois.
  • 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_69d7bdf2b43c819098ae5aa68e61ea58 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e5dbdb88190a1b06721ada51627 completed April 10, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6850703948190984acf9e434cd2a7 completed May 2, 2026, 11:13 p.m.
Created at: April 9, 2026, 5:29 p.m.