Triple

T1498077
Position Surface form Disambiguated ID Type / Status
Subject Jude Law E29731 entity
Predicate hasChild P369 FINISHED
Object Rafferty Law E104147 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: Rafferty Law | Statement: [Jude Law, hasChild, Rafferty Law]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rafferty Law
Context triple: [Jude Law, hasChild, Rafferty Law]
  • A. Rafferty Law chosen
    Rafferty Law is a British model and actor, best known as the son of actors Jude Law and Sadie Frost.
  • B. Cobb, Fendley & Associates
    Cobb, Fendley & Associates is an architecture and engineering firm known for providing design and technical services on major civic and cultural projects.
  • C. Clivillés & Cole
    Clivillés & Cole were a prominent American production and remix duo, best known for their work as C+C Music Factory and for shaping early 1990s dance and pop music.
  • D. Waddell & Hardesty
    Waddell & Hardesty was an American engineering and architectural firm known for designing major steel bridges and other large-scale infrastructure projects in the early 20th century.
  • E. Alston & Bird
    Alston & Bird is a major U.S.-based law firm known for its corporate, litigation, and regulatory practices and its strong presence in Washington, D.C. and other key markets.
  • 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_69a498dba1d8819093b46a3a8d2485f1 completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c6ef5ce88190a6b520525a6d42a3 completed March 1, 2026, 11:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad1caf8b288190b428cf903db2c107 completed March 8, 2026, 6:52 a.m.
Created at: March 1, 2026, 8:12 p.m.