Triple

T21798008
Position Surface form Disambiguated ID Type / Status
Subject David Gelb E538151 entity
Predicate producerOf P490 FINISHED
Object Street Food 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: Street Food | Statement: [David Gelb, producerOf, Street Food]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Street Food
Context triple: [David Gelb, producerOf, Street Food]
  • A. Street Food chosen
    Street Food is a Netflix documentary series that explores vibrant local cuisines and the stories of street vendors around the world.
  • B. Street Food: Asia
    Street Food: Asia is a Netflix documentary series that explores the stories, culture, and culinary traditions behind iconic street food vendors across various Asian countries.
  • C. Road Food
    Road Food is a 1974 rock album by Canadian band The Guess Who, known for its blend of hard rock and pop influences during the group’s later period.
  • D. Street Food: Latin America
    Street Food: Latin America is a Netflix documentary series that explores the diverse street food cultures, dishes, and vendors across various Latin American countries.
  • E. Food Circus
    Food Circus is a grocery store where the character Naomi Harper is employed in the television series "Mama's Family."
  • 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_69e0c4733f4081909a86622e7e6d15d2 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f077fb87848190b6df9a9d1c5336af completed April 28, 2026, 9:03 a.m.
Created at: April 16, 2026, 6:53 p.m.