Triple

T4289686
Position Surface form Disambiguated ID Type / Status
Subject Kate Beckinsale E97356 entity
Predicate child P120 FINISHED
Object Lily Mo Sheen E375778 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: Lily Mo Sheen | Statement: [Kate Beckinsale, child, Lily Mo Sheen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lily Mo Sheen
Context triple: [Kate Beckinsale, child, Lily Mo Sheen]
  • A. Lily Mo Sheen chosen
    Lily Mo Sheen is a British-American actress and the daughter of actors Michael Sheen and Kate Beckinsale.
  • B. Lily Walsh
    Lily Walsh is a central, long-running character on the American soap opera "As the World Turns," known for her complex family ties and dramatic storylines.
  • C. Lily Rose Beatrice Allen
    Lily Rose Beatrice Allen is an English singer, songwriter, and actress known for her sharp, witty pop songs and outspoken public persona.
  • D. Isla Dawson
    Isla Dawson is a remote Chilean island in southern Patagonia, located within the Strait of Magellan and known for its harsh climate and historical use as a mission and penal colony.
  • E. Samantha Gwendoline Sheffield
    Samantha Gwendoline Sheffield is a British businesswoman and the wife of former UK Prime Minister David Cameron, known publicly as Samantha Cameron.
  • 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_69b3454595848190a0e6bbb6a2bea040 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b35061f5448190b3356b29a9129160 completed March 12, 2026, 11:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5c7307e3481909dfb55018f359589 completed March 14, 2026, 8:38 p.m.
Created at: March 12, 2026, 11:08 p.m.