Triple

T15763691
Position Surface form Disambiguated ID Type / Status
Subject Tammy Collins E382163 entity
Predicate name P16 FINISHED
Object Tammy Collins E382163 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: Tammy Collins | Statement: [Tammy Collins, name, Tammy Collins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tammy Collins
Context triple: [Tammy Collins, name, Tammy Collins]
  • A. Tammy Collins chosen
    Tammy Collins is the wife of Grammy-winning gospel musician and choir director Kirk Franklin, known for her supportive role in his personal life and ministry.
  • B. Tammy Townsend
    Tammy Townsend is an American actress and singer best known for her roles in television series such as "Family Matters" and "K.C. Undercover."
  • C. Tammy Campbell
    Tammy Campbell is the daughter of advertising executive Pete Campbell in the television series "Mad Men."
  • D. Lori Collins
    Lori Collins is a central character in the comedy film "Ted," known as John Bennett’s long-suffering girlfriend who pushes him to grow up and choose between her and his crude, living teddy bear best friend.
  • E. Tammy Lucas
    Tammy Lucas is an American R&B singer and songwriter known for her collaborations with prominent hip-hop artists and producers in the 1990s.
  • 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_69d86da09a10819082fe9797b23e4664 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e050b6c9fc8190a1bcf763c4b04b12 completed April 16, 2026, 3 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbbd605c8190ae2b1289ae9570c3 completed May 10, 2026, 1:13 a.m.
Created at: April 10, 2026, 4:47 a.m.