Triple

T17946721
Position Surface form Disambiguated ID Type / Status
Subject Maja Einstein E448720 entity
Predicate placeOfResidence P75 FINISHED
Object Princeton 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: Princeton | Statement: [Maja Einstein, placeOfResidence, Princeton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Princeton
Context triple: [Maja Einstein, placeOfResidence, Princeton]
  • A. Princeton chosen
    Princeton is a historic New Jersey town best known as the site of the pivotal 1777 Battle of Princeton during the American Revolutionary War and as home to Princeton University.
  • B. Princeton
    Princeton is a small city in southern West Virginia known as a regional hub for commerce, education, and access to outdoor recreation in the Appalachian region.
  • C. Princeton
    Princeton is a small but rapidly growing city in Collin County, Texas, situated in the northeastern part of the Dallas–Fort Worth metropolitan area.
  • D. Princeton
    Princeton is a small unincorporated community in Colusa County, California, known for its agricultural surroundings in the Sacramento Valley.
  • E. Princeton
    Princeton is a small city in central Wisconsin known for its historic downtown, outdoor recreation along the Fox River, and popular weekly flea market.
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4ad99df408190a8a4e3d21c03fe71 completed April 19, 2026, 10:25 a.m.
Created at: April 10, 2026, 10:21 a.m.