Triple

T20191622
Position Surface form Disambiguated ID Type / Status
Subject Lucina E492990 entity
Predicate relative P37 FINISHED
Object Lissa
Lissa is a cheerful princess of the Halidom of Ylisse and a playable character from the video game Fire Emblem Awakening.
 E1417412 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: Lissa | Statement: [Lucina, relative, Lissa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lissa
Context triple: [Lucina, relative, Lissa]
  • A. Lissa
    Lissa is a historic town in western Poland, known today as Leszno, that was once part of Germany and is notable as the birthplace of several prominent Jewish and intellectual figures.
  • B. Marina
    Marina is the eccentric, childlike porn actress who becomes the obsessive focus of a recently released psychiatric patient in Pedro Almodóvar’s dark romantic comedy film "Tie Me Up! Tie Me Down!".
  • C. Marina
    Marina is a recurring comedic character in the long-running British sitcom "Last of the Summer Wine," known for her flirtatious relationship with the married Howard.
  • D. Marina
    Marina is a female given name of Latin origin, commonly used in various cultures and often associated with the sea.
  • E. Marina
    Marina is a 2012 Tamil coming-of-age drama film that helped establish Sivakarthikeyan as a leading actor in the Tamil film industry.
  • 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: Lissa
Triple: [Lucina, relative, Lissa]
Generated description
Lissa is a cheerful princess of the Halidom of Ylisse and a playable character from the video game Fire Emblem Awakening.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lissa
Target entity description: Lissa is a cheerful princess of the Halidom of Ylisse and a playable character from the video game Fire Emblem Awakening.
  • A. Lissa
    Lissa is a historic town in western Poland, known today as Leszno, that was once part of Germany and is notable as the birthplace of several prominent Jewish and intellectual figures.
  • B. Marina
    Marina is the eccentric, childlike porn actress who becomes the obsessive focus of a recently released psychiatric patient in Pedro Almodóvar’s dark romantic comedy film "Tie Me Up! Tie Me Down!".
  • C. Marina
    Marina is a 2012 Tamil coming-of-age drama film that helped establish Sivakarthikeyan as a leading actor in the Tamil film industry.
  • D. Marina
    Marina is a recurring comedic character in the long-running British sitcom "Last of the Summer Wine," known for her flirtatious relationship with the married Howard.
  • E. Marina
    Marina is a female given name of Latin origin, commonly used in various cultures and often associated with the sea.
  • 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_69da6268a034819081cbd9ea5a1c9475 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66ad593f88190a1e534fed38b3cd7 completed April 20, 2026, 6:05 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0843e4cc088190a33f932359490196 completed May 16, 2026, 10:16 a.m.
NEDg Description generation batch_6a0844c0f9ec81909773fa613e9aca08 completed May 16, 2026, 10:19 a.m.
NED2 Entity disambiguation (via description) batch_6a084591f43481908e11348b21721b8a completed May 16, 2026, 10:23 a.m.
Created at: April 11, 2026, 11:37 p.m.