Triple

T23067033
Position Surface form Disambiguated ID Type / Status
Subject Tyler Self E575071 entity
Predicate relative P37 FINISHED
Object Lauren Self 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: Lauren Self | Statement: [Tyler Self, relative, Lauren Self]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lauren Self
Context triple: [Tyler Self, relative, Lauren Self]
  • A. Lauren Self chosen
    Lauren Self is the daughter of Hall of Fame college basketball coach Bill Self.
  • B. Lauren Reynolds
    Lauren Reynolds is a central character in the 2013 indie drama film "Breathe In," portrayed as a young woman whose arrival disrupts the emotional equilibrium of a suburban family.
  • C. Lauren Reynolds
    Lauren Reynolds is a character in the romantic comedy film "Blended," which stars Adam Sandler and Drew Barrymore.
  • D. Lauren Harris
    Lauren Harris is a central character in the British television drama series "Fat Friends," which follows the lives, relationships, and weight-loss struggles of members of a slimming club in Leeds.
  • E. Lauren Harris
    Lauren Harris is the daughter of Iron Maiden bassist and founder Steve Harris and is known as a rock singer and musician in her own right.
  • 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_69e245bd6e4c8190bb8942245b68cad5 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f189a4e2fc81909704333306737f80 completed April 29, 2026, 4:31 a.m.
Created at: April 17, 2026, 3:55 p.m.