Triple

T19872148
Position Surface form Disambiguated ID Type / Status
Subject Such Good Friends E477544 entity
Predicate starred P5563 FINISHED
Object Ken Howard 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: Ken Howard | Statement: [Such Good Friends, starred, Ken Howard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ken Howard
Context triple: [Such Good Friends, starred, Ken Howard]
  • A. Ken Howard chosen
    Ken Howard was an American actor best known for his roles in film, television, and theater, including his portrayal of Thomas Jefferson in the musical film "1776."
  • B. Scott Howard
    Scott Howard is the teenage protagonist of the 1985 comedy film "Teen Wolf," who discovers he has inherited the ability to transform into a werewolf.
  • C. Donald Howard
    Donald Howard was a British politician best known for serving on the controversial Simon Commission that investigated constitutional reform in colonial India.
  • D. Steve Howard
    Steve Howard is a British trumpeter best known for his work with Paul McCartney and Wings during the 1970s.
  • E. Peter Howard
    Peter Howard was a British journalist, playwright, and leader in the Moral Re-Armament movement, known for his politically charged writings and Christian-influenced social activism in the mid-20th century.
  • 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_69d8e51e7d948190aedbcd6c30361c39 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e658d826f88190be04188997952d1b completed April 20, 2026, 4:48 p.m.
Created at: April 10, 2026, 1:51 p.m.