Triple

T19727960
Position Surface form Disambiguated ID Type / Status
Subject Antonio and Mellida E473775 entity
Predicate mainCharacter P1183 FINISHED
Object Mellida
Mellida is a central character in John Marston’s late-Elizabethan play "Antonio and Mellida," known for her role in the tragicomic love story that drives the drama.
E1392914 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: Mellida | Statement: [Antonio and Mellida, mainCharacter, Mellida]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mellida
Context triple: [Antonio and Mellida, mainCharacter, Mellida]
  • A. Savena
    Savena is a river in northern Italy that flows through the Emilia-Romagna region, including the area near Bologna.
  • B. Saraghina
    Saraghina is a memorable, sensual character from Federico Fellini’s film "8½," embodying the protagonist’s early, taboo experiences with desire and womanhood.
  • C. Masuleh
    Masuleh is a historic stepped village in northern Iran renowned for its terraced architecture built into the mountainside and its scenic foggy landscapes.
  • D. Meziella
    Meziella is a small, lesser-known genus of flowering plants within the water milfoil family Haloragaceae.
  • E. Mellé
    Mellé is a French surname most notably borne by Gil Mellé, an American jazz musician and film and television composer.
  • 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: Mellida
Triple: [Antonio and Mellida, mainCharacter, Mellida]
Generated description
Mellida is a central character in John Marston’s late-Elizabethan play "Antonio and Mellida," known for her role in the tragicomic love story that drives the drama.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mellida
Target entity description: Mellida is a central character in John Marston’s late-Elizabethan play "Antonio and Mellida," known for her role in the tragicomic love story that drives the drama.
  • A. Savena
    Savena is a river in northern Italy that flows through the Emilia-Romagna region, including the area near Bologna.
  • B. Saraghina
    Saraghina is a memorable, sensual character from Federico Fellini’s film "8½," embodying the protagonist’s early, taboo experiences with desire and womanhood.
  • C. Masuleh
    Masuleh is a historic stepped village in northern Iran renowned for its terraced architecture built into the mountainside and its scenic foggy landscapes.
  • D. Meziella
    Meziella is a small, lesser-known genus of flowering plants within the water milfoil family Haloragaceae.
  • E. Mellé
    Mellé is a French surname most notably borne by Gil Mellé, an American jazz musician and film and television composer.
  • 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_69d8e517ebd48190979ee76723bcfadf completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e649fa1bc481908a9e7cf4fc52f75c completed April 20, 2026, 3:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07b4f0728881909ccadf9e738e371c completed May 16, 2026, 12:06 a.m.
NEDg Description generation batch_6a07b5e9961881908f224154ec12c366 completed May 16, 2026, 12:10 a.m.
NED2 Entity disambiguation (via description) batch_6a07b67964b481909af269c6b5db6527 completed May 16, 2026, 12:12 a.m.
Created at: April 10, 2026, 1:47 p.m.