Triple

T15920693
Position Surface form Disambiguated ID Type / Status
Subject Come Away with Me E386084 entity
Predicate producer P490 FINISHED
Object Craig Street 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: Craig Street | Statement: [Come Away with Me, producer, Craig Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Craig Street
Context triple: [Come Away with Me, producer, Craig Street]
  • A. Craig Street chosen
    Craig Street is an American record producer known for his work on acclaimed jazz, soul, and folk albums, often characterized by warm, intimate, and atmospheric soundscapes.
  • B. Craig Street
    Craig Street is a notable thoroughfare in Pittsburgh, Pennsylvania, known for its mix of shops, restaurants, and proximity to local universities.
  • C. Dean Street
    Dean Street is a notable thoroughfare in London’s Soho district, known for its historic buildings, creative industries, and vibrant nightlife.
  • D. Charlotte Street
    Charlotte Street is a street in Manchester, England, notable for being part of the city's Chinatown district.
  • E. Callowhill Street
    Callowhill Street is a major east–west thoroughfare in Philadelphia, Pennsylvania, known for its industrial history and role as a key connector near the city’s downtown.
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156818cbc819086c956475ad23825 completed April 16, 2026, 9:37 p.m.
Created at: April 10, 2026, 4:52 a.m.