Triple

T14414184
Position Surface form Disambiguated ID Type / Status
Subject Ammonite E357405 entity
Predicate director P255 FINISHED
Object Francis Lee E853721 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: Francis Lee | Statement: [Ammonite, director, Francis Lee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Francis Lee
Context triple: [Ammonite, director, Francis Lee]
  • A. Francis Lee chosen
    Francis Lee is a British filmmaker and screenwriter best known for his intimate, character-driven dramas such as "God's Own Country" and "Ammonite."
  • B. Garth Davis
    Garth Davis is an Australian film and television director best known for his critically acclaimed feature "Lion" and work on the series "Top of the Lake."
  • C. Alex Gansa
    Alex Gansa is an American television writer and producer best known for co-creating and showrunning the acclaimed political thriller series "Homeland."
  • D. Wes Ball
    Wes Ball is an American film director best known for helming the Maze Runner science-fiction film series.
  • E. Dan Goor
    Dan Goor is an American television writer and producer best known for co-creating the comedy series "Brooklyn Nine-Nine" and his work on shows like "Parks and Recreation."
  • 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_69d82793421c8190861eb0e673b085de completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de90cc99208190a2313b1acfb5d802 completed April 14, 2026, 7:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd552a75ec8190b966d509d315ca60 completed May 8, 2026, 3:14 a.m.
Created at: April 10, 2026, 1:17 a.m.