Triple

T19913229
Position Surface form Disambiguated ID Type / Status
Subject Prisoner E478599 entity
Predicate producer P490 FINISHED
Object Don Was 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: Don Was | Statement: [Prisoner, producer, Don Was]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Don Was
Context triple: [Prisoner, producer, Don Was]
  • A. Don Was chosen
    Don Was is an American musician and Grammy-winning record producer best known for his work with artists across rock, blues, and pop, and as the longtime president of Blue Note Records.
  • B. Johnny Was
    "Johnny Was" is a socially conscious reggae song by Bob Marley and the Wailers, known for its poignant storytelling about violence and loss.
  • C. Don Most
    Don Most is an American actor and singer best known for playing Ralph Malph on the classic television sitcom "Happy Days."
  • D. Don Paul
    Don Paul is an American film director and animator best known for co-directing the DreamWorks animated feature "The Road to El Dorado."
  • E. Hal Walker
    Hal Walker was an American film director best known for his work on mid-20th-century Hollywood comedies, including several popular Bing Crosby and Bob Hope "Road to..." films.
  • 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_69d8e520682081909892916424699bd5 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e659917fdc8190bf29bfdab0fe8f85 completed April 20, 2026, 4:51 p.m.
Created at: April 10, 2026, 1:53 p.m.