Triple

T11404612
Position Surface form Disambiguated ID Type / Status
Subject Serena E270203 entity
Predicate spouse P13 FINISHED
Object Robbins E274002 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: Robbins | Statement: [Serena, spouse, Robbins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robbins
Context triple: [Serena, spouse, Robbins]
  • A. Robbins
    Robbins is the middle name of H. R. Haldeman, the influential White House Chief of Staff under U.S. President Richard Nixon and a central figure in the Watergate scandal.
  • B. Robbins chosen
    Robbins is a common English-language surname borne by numerous notable individuals across fields such as entertainment, literature, and academia.
  • C. Robbins
    Robbins is a small unincorporated community in Sutter County, California, known for its rural agricultural setting in the Sacramento Valley.
  • D. Robberts
    Robberts is the given name of Charles Robberts Swart, the first State President of South Africa.
  • E. Robards
    Robards is a surname most prominently associated with the American stage and film actor Jason Robards.
  • 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_69d6aaddeaa8819088b30ef7b50598c9 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8014ab46881909fa1d425926c617b completed April 9, 2026, 7:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69e58d56608481908dbb19daa2abfc0a completed April 20, 2026, 2:20 a.m.
Created at: April 8, 2026, 9:34 p.m.