Triple

T8381070
Position Surface form Disambiguated ID Type / Status
Subject Eric Liddell E197688 entity
Predicate sibling P363 FINISHED
Object Rob Liddell E197688 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: Rob Liddell | Statement: [Eric Liddell, sibling, Rob Liddell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rob Liddell
Context triple: [Eric Liddell, sibling, Rob Liddell]
  • A. Rob Liddell chosen
    Rob Liddell was the brother of Scottish Olympic champion and Christian missionary Eric Liddell, belonging to the same notable Liddell family.
  • B. Don Liddell
    Don Liddell was a British Army officer and intelligence figure who served as Director of Military Intelligence at the War Office during and after World War I.
  • C. Chris Liddell
    Chris Liddell is a New Zealand-born businessman and former corporate executive who served as White House Deputy Chief of Staff for Policy Coordination under U.S. President Donald Trump.
  • D. Tommy Smith
    Tommy Smith is a former professional soccer player best known for his time in the North American Soccer League, including a notable stint with the Los Angeles Aztecs.
  • E. Tommy Smith
    Tommy Smith was an early 20th-century Canadian ice hockey forward known for his prolific goal scoring in professional leagues such as the NHA and NHL.
  • 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_69ca82f64c188190af4e1608036b865d completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb80dc96048190887d7df8bce5c1fd completed March 31, 2026, 8:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce02c0664481908f3c79246350a248 completed April 2, 2026, 5:46 a.m.
Created at: March 30, 2026, 6:02 p.m.