Triple

T9983214
Position Surface form Disambiguated ID Type / Status
Subject Mykelti Williamson E196503 entity
Predicate notableWork P4 FINISHED
Object Ali E63925 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: Ali | Statement: [Mykelti Williamson, notableWork, Ali]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ali
Context triple: [Mykelti Williamson, notableWork, Ali]
  • A. Ali chosen
    "Ali" is a biographical sports drama film about boxer Muhammad Ali, noted for Emmanuel Lubezki’s distinctive cinematography.
  • B. Ali
    Ali is a common Arabic male given name meaning "exalted" or "noble," widely used across the Muslim world and historically associated with prominent religious and political figures.
  • C. Ali
    Ali is a hip-hop artist known for contributing a featured verse to Nelly’s hit single “Air Force Ones.”
  • D. Ali
    Ali is a heroic slave and central figure in the ballet "Le Corsaire," known for his virtuosic and demanding male variations.
  • E. Alan
    Alan is a masculine given name of Celtic origin that has been widely used in English-speaking countries.
  • 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_69ca82efbce081908179b4b9c65096eb completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb8bdc0388190bbbd4bdc5ac3adec completed April 2, 2026, 12:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69d257f3c59481909b90896be0f3a870 completed April 5, 2026, 12:39 p.m.
Created at: March 30, 2026, 8:49 p.m.