Triple

T18819617
Position Surface form Disambiguated ID Type / Status
Subject Rafferty Law E460227 entity
Predicate hasSibling P363 FINISHED
Object Iris Law 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: Iris Law | Statement: [Rafferty Law, hasSibling, Iris Law]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Iris Law
Context triple: [Rafferty Law, hasSibling, Iris Law]
  • A. Iris Law chosen
    Iris Law is a British model and actress known for her high-fashion campaigns and emerging film roles, as well as being the daughter of actors Jude Law and Sadie Frost.
  • B. Iris Wheeler
    Iris Wheeler is a central, long-running fictional character from the American soap opera "Another World," known for her complex relationships and dramatic storylines.
  • C. Iris (TV series)
    Iris is a South Korean espionage action-thriller television series known for its high production values, intricate spy plot, and starring role by Byung-hun Lee.
  • D. Iris Chase
    Iris Chase is the complex, introspective narrator of Margaret Atwood’s novel "The Blind Assassin," whose recollections unravel a multigenerational family saga marked by betrayal, secrecy, and shifting power.
  • E. Iris
    Iris is an Italian verismo opera by Pietro Mascagni, first performed in 1898 and noted for its exotic Japanese setting and lush orchestration.
  • 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_69d8dcf94c288190a06dea029ae4b223 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a6b8b7d88190a8828746176776ea completed April 20, 2026, 4:08 a.m.
Created at: April 10, 2026, 11:55 a.m.