Triple

T3121476
Position Surface form Disambiguated ID Type / Status
Subject Wendy Melvoin E65193 entity
Predicate hasPartnership P1136 FINISHED
Object Lisa Coleman E214887 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: Lisa Coleman | Statement: [Wendy Melvoin, hasPartnership, Lisa Coleman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lisa Coleman
Context triple: [Wendy Melvoin, hasPartnership, Lisa Coleman]
  • A. Lisa Coleman chosen
    Lisa Coleman is an American musician and composer best known as a member of Prince’s backing band The Revolution and for her extensive film and television scoring work.
  • B. Colleen Bell
    Colleen Bell is an American television producer and political appointee who served as the U.S. Ambassador to Hungary.
  • C. Charlotte Coleman
    Charlotte Coleman was a British actress best known for her role as Scarlett in the romantic comedy film "Four Weddings and a Funeral."
  • D. Ann McKean
    Ann McKean was a daughter of Thomas McKean, a prominent American Founding Father and signer of the Declaration of Independence.
  • E. Colleen Howe
    Colleen Howe was an American sports agent and business manager best known for managing and promoting the career and legacy of her husband, hockey legend Gordie Howe.
  • 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_69ad8580c72481909672d37acf647893 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada5295cd481908d52e165538c67fa completed March 8, 2026, 4:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4cdc422d08190aa67bc39619c3290 completed March 14, 2026, 2:53 a.m.
Created at: March 8, 2026, 3:04 p.m.