Triple

T20883049
Position Surface form Disambiguated ID Type / Status
Subject Snowball Express E514200 entity
Predicate screenwriter P2831 FINISHED
Object Don Tait 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: Don Tait | Statement: [Snowball Express, screenwriter, Don Tait]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Don Tait
Context triple: [Snowball Express, screenwriter, Don Tait]
  • A. Don Tait chosen
    Don Tait was an American screenwriter best known for his work on family-friendly Disney films in the 1960s and 1970s.
  • B. Tom Tait
    Tom Tait is an American volleyball coach best known as the founding coach who built Penn State’s men’s volleyball program into a national powerhouse.
  • C. Bill Cayton
    Bill Cayton was an American boxing manager and promoter best known for co-managing heavyweight champion Mike Tyson during the early part of his professional career.
  • D. Dan Talbot
    Dan Talbot was an influential American film distributor and exhibitor known for championing foreign and independent cinema in the United States.
  • E. Dick Tufeld
    Dick Tufeld was an American voice actor best known as the iconic voice of the Robot in the classic television series "Lost in Space."
  • 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c67b03088190be7cbcde8c59509a completed April 21, 2026, 12:36 a.m.
Created at: April 16, 2026, 12:46 p.m.