Triple

T16912709
Position Surface form Disambiguated ID Type / Status
Subject Mary MacLaren E410240 entity
Predicate spouse P13 FINISHED
Object Robert Gordon E958877 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: Robert Gordon | Statement: [Mary MacLaren, spouse, Robert Gordon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Gordon
Context triple: [Mary MacLaren, spouse, Robert Gordon]
  • A. Robert Gordon
    Robert Gordon was an American screenwriter best known for writing the cult science-fiction comedy film "Galaxy Quest."
  • B. Robert Gordon chosen
    Robert Gordon was an American rockabilly singer known for reviving 1950s rock and roll with his powerful vocals and collaborations with noted guitarists like Link Wray and Chris Spedding.
  • C. Robert Gordon
    Robert Gordon was a Scottish merchant and philanthropist whose legacy in education led to the founding of the institution that became Robert Gordon University in Aberdeen.
  • D. Robert Gordon
    Robert Gordon is a music industry figure best known for co-founding the influential British electronic music label Warp Records.
  • E. Robert J. Gordon
    Robert J. Gordon is an American economist best known for his influential work on inflation, unemployment, and long-run economic growth, particularly his analyses of productivity and the U.S. economy.
  • 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_69d886c7b1e481908c3766dfa8c13458 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3ca3e6b9481909fbaeb0bddd7e3b2 completed April 18, 2026, 6:15 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c7be679c8190b9d0b0b9cfe185d3 completed May 10, 2026, 6 p.m.
Created at: April 10, 2026, 5:30 a.m.