Triple

T20191628
Position Surface form Disambiguated ID Type / Status
Subject Lucina E492990 entity
Predicate relative P37 FINISHED
Object Severa
Severa is a tsundere-style mercenary and playable character from the video game Fire Emblem Awakening, known as the future daughter of Cordelia who later appears in Fire Emblem Fates under the alias Selena.
 E1417093 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: Severa | Statement: [Lucina, relative, Severa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Severa
Context triple: [Lucina, relative, Severa]
  • A. Severin
    Severin is a locality within the municipality of Persenbeug-Gottsdorf in Lower Austria.
  • B. Severin
    Severin is a fictional character in John Irving’s novel "The 158-Pound Marriage," involved in the complex, emotionally fraught partner-swapping relationships at the center of the story.
  • C. Sevez
    Sevez is a French surname most notably borne by François Sevez, a French general.
  • D. Rupea
    Rupea is a small historic town in central Romania, known for its medieval hilltop fortress and location within Brașov County in Transylvania.
  • E. Sebastia
    Sebastia is the historical name for the city of Sivas in central Anatolia, an important regional center through Roman, Byzantine, and Ottoman periods.
  • 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: Severa
Triple: [Lucina, relative, Severa]
Generated description
Severa is a tsundere-style mercenary and playable character from the video game Fire Emblem Awakening, known as the future daughter of Cordelia who later appears in Fire Emblem Fates under the alias Selena.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Severa
Target entity description: Severa is a tsundere-style mercenary and playable character from the video game Fire Emblem Awakening, known as the future daughter of Cordelia who later appears in Fire Emblem Fates under the alias Selena.
  • A. Severin
    Severin is a locality within the municipality of Persenbeug-Gottsdorf in Lower Austria.
  • B. Severin
    Severin is a fictional character in John Irving’s novel "The 158-Pound Marriage," involved in the complex, emotionally fraught partner-swapping relationships at the center of the story.
  • C. Sevez
    Sevez is a French surname most notably borne by François Sevez, a French general.
  • D. Rupea
    Rupea is a small historic town in central Romania, known for its medieval hilltop fortress and location within Brașov County in Transylvania.
  • E. Sebastia
    Sebastia is the historical name for the city of Sivas in central Anatolia, an important regional center through Roman, Byzantine, and Ottoman periods.
  • 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_6a083c86799c8190844085d482c88ffe completed May 16, 2026, 9:44 a.m.
NEDg Description generation batch_6a083d8781b48190be4043a3747fd0ef completed May 16, 2026, 9:48 a.m.
NED2 Entity disambiguation (via description) batch_6a083f2d7db081908c281445210f551b completed May 16, 2026, 9:55 a.m.
Created at: April 11, 2026, 11:37 p.m.