Triple

T14766285
Position Surface form Disambiguated ID Type / Status
Subject Ghost Whisperer E347003 entity
Predicate starring P1507 FINISHED
Object Aisha Tyler E869513 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: Aisha Tyler | Statement: [Ghost Whisperer, starring, Aisha Tyler]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aisha Tyler
Context triple: [Ghost Whisperer, starring, Aisha Tyler]
  • A. Aisha Tyler chosen
    Aisha Tyler is an American actress, comedian, director, and television host known for roles in shows like "Friends," "Archer," and "Criminal Minds," as well as for hosting "Whose Line Is It Anyway?"
  • B. Ashley Curry
    Ashley Curry is an American local government official serving as the mayor of Vestavia Hills, Alabama.
  • C. Chrishell Stause
    Chrishell Stause is an American actress and real estate agent best known for her role on the reality series "Selling Sunset" and appearances in various soap operas.
  • D. Gail Simmons
    Gail Simmons is a Canadian food writer and culinary expert best known as a longtime judge on the reality cooking competition show "Top Chef."
  • E. Michaela Zee
    Michaela Zee is an American voice actress and the daughter of actress Ming-Na Wen.
  • 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_69d822e8896c819091169882f9b20486 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7f576c881909da70627f5897c94 completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0cf68d94819093567bc630f67b60 completed May 8, 2026, 4:19 p.m.
Created at: April 10, 2026, 1:30 a.m.