Triple

T23152889
Position Surface form Disambiguated ID Type / Status
Subject Mouth to Mouth E578365 entity
Predicate hasCharacter P2308 FINISHED
Object Saffron
Saffron is a character from the film "Mouth to Mouth," likely involved in its central interpersonal and dramatic conflicts.
 E1574810 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: Saffron | Statement: [Mouth to Mouth, hasCharacter, Saffron]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Saffron
Context triple: [Mouth to Mouth, hasCharacter, Saffron]
  • A. Saffron
    Saffron is a fictional character from the British sitcom "Absolutely Fabulous," known as the sensible and responsible daughter of the eccentric Edina Monsoon.
  • B. Krokos Kozanis saffron
    Krokos Kozanis saffron is a premium Greek red saffron renowned for its exceptional aroma, flavor, and high quality, produced in the Kozani region.
  • C. Fenoglio
    Fenoglio is the fictional author within Cornelia Funke’s "Inkheart" trilogy whose written stories have the power to shape the magical world of the books.
  • D. Haldi
    Haldi is the chief war and national god of the ancient Kingdom of Urartu, central to its state religion and royal ideology.
  • E. Fennel
    Fennel is a Lisp-like programming language that compiles to Lua, offering a minimal, functional syntax with seamless integration into the Lua ecosystem.
  • 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: Saffron
Triple: [Mouth to Mouth, hasCharacter, Saffron]
Generated description
Saffron is a character from the film "Mouth to Mouth," likely involved in its central interpersonal and dramatic conflicts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Saffron
Target entity description: Saffron is a character from the film "Mouth to Mouth," likely involved in its central interpersonal and dramatic conflicts.
  • A. Saffron
    Saffron is a fictional character from the British sitcom "Absolutely Fabulous," known as the sensible and responsible daughter of the eccentric Edina Monsoon.
  • B. Krokos Kozanis saffron
    Krokos Kozanis saffron is a premium Greek red saffron renowned for its exceptional aroma, flavor, and high quality, produced in the Kozani region.
  • C. Fenoglio
    Fenoglio is the fictional author within Cornelia Funke’s "Inkheart" trilogy whose written stories have the power to shape the magical world of the books.
  • D. Haldi
    Haldi is the chief war and national god of the ancient Kingdom of Urartu, central to its state religion and royal ideology.
  • E. Fennel
    Fennel is a Lisp-like programming language that compiles to Lua, offering a minimal, functional syntax with seamless integration into the Lua ecosystem.
  • 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_69e245fb8de081908f0eba7b5fd75bc4 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18efaa1fc81908fb1987dbf732f46 completed April 29, 2026, 4:54 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c309a54b881909b53677488534b7c completed May 19, 2026, 9:42 a.m.
NEDg Description generation batch_6a0c3105ab388190b135f5c7de240023 completed May 19, 2026, 9:44 a.m.
NED2 Entity disambiguation (via description) batch_6a0c317738d08190adfe51d2b8075f1b completed May 19, 2026, 9:46 a.m.
Created at: April 17, 2026, 4:01 p.m.