Triple

T7288046
Position Surface form Disambiguated ID Type / Status
Subject Soul Food E163923 entity
Predicate character P662 FINISHED
Object Lem
Lem is a character from the television drama "Soul Food," known as the hardworking, often troubled husband of Bird who struggles to balance family responsibilities with his criminal past.
E653577 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: Lem | Statement: [Soul Food, character, Lem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lem
Context triple: [Soul Food, character, Lem]
  • A. Lem
    Lem is a Polish surname most famously borne by science fiction writer and philosopher Stanisław Lem.
  • B. Lemi
    Lemi is a small rural municipality in southeastern Finland known for its lakes, forests, and traditional Karelian culture.
  • C. Exelmans
    Exelmans is a Paris Métro station on Line 9 located in the 16th arrondissement of Paris, France.
  • D. Leo
    Leo is an animated comedy film associated with Adam Sandler’s Happy Madison Productions, featuring a humorous, family-friendly story.
  • E. Leo
    Leo is a zodiac constellation and astrological sign traditionally associated with the lion, symbolizing courage, leadership, and creativity.
  • 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: Lem
Triple: [Soul Food, character, Lem]
Generated description
Lem is a character from the television drama "Soul Food," known as the hardworking, often troubled husband of Bird who struggles to balance family responsibilities with his criminal past.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lem
Target entity description: Lem is a character from the television drama "Soul Food," known as the hardworking, often troubled husband of Bird who struggles to balance family responsibilities with his criminal past.
  • A. Lem
    Lem is a Polish surname most famously borne by science fiction writer and philosopher Stanisław Lem.
  • B. Lemi
    Lemi is a small rural municipality in southeastern Finland known for its lakes, forests, and traditional Karelian culture.
  • C. Exelmans
    Exelmans is a Paris Métro station on Line 9 located in the 16th arrondissement of Paris, France.
  • D. Leo
    Leo is a zodiac constellation and astrological sign traditionally associated with the lion, symbolizing courage, leadership, and creativity.
  • E. Leo
    Leo is an animated comedy film associated with Adam Sandler’s Happy Madison Productions, featuring a humorous, family-friendly story.
  • 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_69c6886093b88190a254b1ce6db8bae7 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6eb6a73fc8190ae5ce81fd3e46d87 completed March 27, 2026, 8:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7db42c8d48190a548c4242b07fb40 completed March 28, 2026, 1:44 p.m.
NEDg Description generation batch_69c7dc794bec819094d848497bd11fc1 completed March 28, 2026, 1:49 p.m.
NED2 Entity disambiguation (via description) batch_69c7dd8117f881908c982c33b3f0e71a completed March 28, 2026, 1:54 p.m.
Created at: March 27, 2026, 2:59 p.m.