Triple

T21850169
Position Surface form Disambiguated ID Type / Status
Subject Tom Skilling E539483 entity
Predicate name P16 FINISHED
Object Tom Skilling 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: Tom Skilling | Statement: [Tom Skilling, name, Tom Skilling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Skilling
Context triple: [Tom Skilling, name, Tom Skilling]
  • A. Tom Skilling chosen
    Tom Skilling is a prominent American meteorologist best known for his long tenure as chief meteorologist at WGN-TV in Chicago.
  • B. Paul Doswell
    Paul Doswell is an English football manager best known for his long and successful spell in charge of Sutton United, including leading them to a famous FA Cup run.
  • C. Tom Ropelewski
    Tom Ropelewski is an American screenwriter and film director known for working on mainstream Hollywood comedies and family films.
  • D. Greg Siple
    Greg Siple is an American cyclist, illustrator, and co-founder of the Adventure Cycling Association, known for helping launch long-distance bicycle touring in the United States.
  • E. Phil Jones
    Phil Jones is an American drummer best known for his work with Tom Petty and the Heartbreakers and on Tom Petty’s solo recordings.
  • 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_69e0c476c3c88190a92d08ebb59a128a completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f0bd582ca48190890648fdee2a0c6e completed April 28, 2026, 1:59 p.m.
Created at: April 16, 2026, 6:55 p.m.