Triple

T20325819
Position Surface form Disambiguated ID Type / Status
Subject Ricky Underwood E492335 entity
Predicate hasLastName P18 FINISHED
Object Underwood 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: Underwood | Statement: [Ricky Underwood, hasLastName, Underwood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Underwood
Context triple: [Ricky Underwood, hasLastName, Underwood]
  • A. Underwood chosen
    Underwood is a surname most prominently associated with the fictional political power couple Frank and Claire Underwood from the television series "House of Cards."
  • B. Underwood
    Underwood is a village in Nottinghamshire, England, known for its semi-rural character and proximity to the town of Eastwood.
  • C. Underwood
    Underwood is a residential suburb located within Logan City in Queensland, Australia, known for its multicultural community and convenient access to Brisbane.
  • D. New Underwood
    New Underwood is a small rural town in western South Dakota known for its agricultural community and proximity to Rapid City.
  • E. Roper
    Roper is a central character in the fantasy novel "The Midnight Bell," around whom much of the story’s action and intrigue revolves.
  • 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_69e0b4a0134081909113563e1c3ba68a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6778f20288190b1862d6be61bfb67 completed April 20, 2026, 6:59 p.m.
Created at: April 16, 2026, 11:21 a.m.