Triple

T16147713
Position Surface form Disambiguated ID Type / Status
Subject Anamaria Marinca E391828 entity
Predicate notableWork P4 FINISHED
Object Storm
Storm is a 2009 European drama film starring Anamaria Marinca that follows a war crimes trial at the International Criminal Tribunal in The Hague.
E1196979 NE FINISHED

How this triple was built (4 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: Storm | Statement: [Anamaria Marinca, notableWork, Storm]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Storm
Context triple: [Anamaria Marinca, notableWork, Storm]
  • A. Storm
    "Storm" is a track by Blue Electric Light, likely featuring an energetic, electrified sound that reflects the band's style.
  • B. Storm
    Storm is a common surname shared by various real and fictional individuals, notably including members of the superhero team the Fantastic Four.
  • C. Storm
    Storm was a professional arena football team based in Tampa Bay, Florida, that competed in the Arena Football League.
  • D. Storm
    Storm is the short name of the Lake Elsinore Storm, a Minor League Baseball team based in Lake Elsinore, California.
  • E. Storm
    "Storm" is a contemporary musical composition by British composer Judith Weir, reflecting her distinctive modern classical style and narrative-driven approach to writing.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Storm
Triple: [Anamaria Marinca, notableWork, Storm]
Generated description
Storm is a 2009 European drama film starring Anamaria Marinca that follows a war crimes trial at the International Criminal Tribunal in The Hague.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Storm
Target entity description: Storm is a 2009 European drama film starring Anamaria Marinca that follows a war crimes trial at the International Criminal Tribunal in The Hague.
  • A. Storm
    Storm is a film project on which Academy Award–winning cinematographer Linus Sandgren contributed his visual expertise.
  • B. Storm
    Storm is a powerful Marvel Comics superhero and longtime member of the X-Men, known for her ability to control the weather.
  • C. Storm
    "Storm" is a 2003 acoustic studio album by Bermudian singer-songwriter Heather Nova, known for its intimate, stripped-down sound and introspective lyrics.
  • D. Storm
    "Storm" is a contemporary musical composition by British composer Judith Weir, reflecting her distinctive modern classical style and narrative-driven approach to writing.
  • E. Storm
    Storm is a professional rugby league club based in Melbourne, Australia, that competes in the National Rugby League (NRL).
  • F. None of above. chosen

Provenance (5 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_69d87f1c65e48190aa2b4c472e9bafc4 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21d9551e081908391061b092ff31b completed April 17, 2026, 11:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7a7dc3481909f933acd72d6feff completed May 10, 2026, 3:12 a.m.
NEDg Description generation batch_69fff81bb0008190947eeff64dc8eb88 completed May 10, 2026, 3:14 a.m.
NED2 Entity disambiguation (via description) batch_69fff8905ce48190b99f8cc3504efba2 completed May 10, 2026, 3:16 a.m.
Created at: April 10, 2026, 5:01 a.m.