Triple

T3819816
Position Surface form Disambiguated ID Type / Status
Subject More American Graffiti E84344 entity
Predicate stars P1956 FINISHED
Object Paul Le Mat E95981 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: Paul Le Mat | Statement: [More American Graffiti, stars, Paul Le Mat]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Le Mat
Context triple: [More American Graffiti, stars, Paul Le Mat]
  • A. Paul Le Mat chosen
    Paul Le Mat is an American actor best known for his breakout role as the hot-rodder John Milner in the coming-of-age film "American Graffiti."
  • B. Ken Burrough
    Ken Burrough was an American professional football wide receiver best known for his Pro Bowl career with the Houston Oilers in the 1970s.
  • C. Frederick Peters
    Frederick Peters was the brother of classic Hollywood actress Carole Lombard, connected to her family life outside her film career.
  • D. Joseph MacDonald
    Joseph MacDonald was an American cinematographer known for his work on numerous classic Hollywood films, particularly in the 1940s and 1950s.
  • E. Francis Carco
    Francis Carco was a French novelist, poet, and journalist associated with bohemian Paris and known for his gritty, atmospheric depictions of urban life and the criminal underworld.
  • 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_69aed931f5908190be2c07af66d4df25 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeea601d408190b09dc486e77488d4 completed March 9, 2026, 3:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b503f75f6c8190b9af77ed212a2774 completed March 14, 2026, 6:45 a.m.
Created at: March 9, 2026, 3:17 p.m.