Triple

T8153405
Position Surface form Disambiguated ID Type / Status
Subject Marlon Williams E190384 entity
Predicate givenName P17 FINISHED
Object Marlon E326461 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: Marlon | Statement: [Marlon Williams, givenName, Marlon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marlon
Context triple: [Marlon Williams, givenName, Marlon]
  • A. Marlon chosen
    Marlon is a masculine given name most famously associated with legendary American actor Marlon Brando.
  • B. Marlon Richards
    Marlon Richards is a British artist and photographer best known as the son of Rolling Stones guitarist Keith Richards and model Anita Pallenberg.
  • C. Duron
    Duron is a budget line of x86-compatible microprocessors developed by AMD as a cost-effective alternative to its Athlon series.
  • D. Lyndon Simmonds
    Lyndon Simmonds is a former professional footballer best known for playing as a forward in the English leagues during the late 20th century.
  • E. Antonio Dawson
    Antonio Dawson is a dedicated and principled detective in the Chicago Police Department’s Intelligence Unit on the television series "Chicago P.D.," known for his strong moral compass and loyalty to his team and family.
  • 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_69ca82bfeb6481909d07b91b5cf69f59 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb44d566b08190a6bb672f9c368806 completed March 31, 2026, 3:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccbf0518688190b519fbe1823b95c2 completed April 1, 2026, 6:45 a.m.
Created at: March 30, 2026, 5:37 p.m.