Triple

T15899120
Position Surface form Disambiguated ID Type / Status
Subject Kevin Reynolds E385537 entity
Predicate directed P7373 FINISHED
Object Fandango E1183139 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: Fandango | Statement: [Kevin Reynolds, directed, Fandango]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fandango
Context triple: [Kevin Reynolds, directed, Fandango]
  • A. Fandango
    Fandango is an Italian film production and distribution company known for producing and promoting a wide range of contemporary Italian and international films.
  • B. Fandango chosen
    Fandango is a 1985 coming-of-age road comedy-drama film about a group of college friends on a final adventure before graduation and the Vietnam War.
  • C. Fandango
    "Fandango" is a song by the German industrial metal band Oomph!, featured on their 1995 album "Trauma."
  • D. Bigas Luna
    Bigas Luna was a Spanish film director known for his sensual, visually striking films that often explored themes of desire, identity, and Spanish cultural stereotypes, including the internationally acclaimed "Jamón Jamón."
  • E. Gigli
    Gigli is a 2003 romantic comedy crime film starring Ben Affleck and Jennifer Lopez that became widely known as a critical and commercial failure.
  • 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_69d86da5b800819083a31be937d738b0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1563bd0688190b6f7a695be0a4625 completed April 16, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5a1b1548190a8579cebf9e71121 completed May 9, 2026, 10:30 p.m.
Created at: April 10, 2026, 4:51 a.m.