Triple

T2865214
Position Surface form Disambiguated ID Type / Status
Subject Colin Hanks E63421 entity
Predicate parent P120 FINISHED
Object Samantha Lewes E97181 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: Samantha Lewes | Statement: [Colin Hanks, parent, Samantha Lewes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Samantha Lewes
Context triple: [Colin Hanks, parent, Samantha Lewes]
  • A. Samantha Lewes chosen
    Samantha Lewes was an American actress best known as Tom Hanks’s first wife and the mother of actors Colin Hanks and Elizabeth Hanks.
  • B. Samantha Winslow
    Samantha Winslow is an American photographer and the wife of renowned film composer John Williams.
  • C. Samantha Thompson
    Samantha Thompson is known as the daughter of American politician and former Illinois governor James R. Thompson.
  • D. Emma Chambers
    Emma Chambers was an English actress best known for her comedic role as Alice Tinker in the television sitcom "The Vicar of Dibley."
  • E. Julia Thorne
    Julia Thorne was an American writer and mental health advocate best known as the first wife of politician John Kerry.
  • 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_69ab4c42fb8c8190b36e161d47c03b81 completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abdfb9e64c819087b1a47caeb174d5 completed March 7, 2026, 8:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69b01da458ec8190ae07237d7e23b302 completed March 10, 2026, 1:33 p.m.
Created at: March 6, 2026, 10:02 p.m.