Triple

T37660839
Position Surface form Disambiguated ID Type / Status
Subject Persona 4 Golden E937713 entity
Predicate addedCharacter P188588 FINISHED
Object Marie
Marie is a mysterious, poetry-writing girl introduced in Persona 4 Golden who becomes a key social link and central figure in the game's new story content.
 E2239036 NE FINISHED

How this triple was built (3 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: Marie | Statement: [Persona 4 Golden, addedCharacter, Marie]
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: Marie
Triple: [Persona 4 Golden, addedCharacter, Marie]
Generated description
Marie is a mysterious, poetry-writing girl introduced in Persona 4 Golden who becomes a key social link and central figure in the game's new story content.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: addedCharacter
Context triple: [Persona 4 Golden, addedCharacter, Marie]
  • A. removedCharacter
    Indicates that a character was taken out or deleted from a text, sequence, or collection.
  • B. exampleCharacter
    Indicates that one entity is an illustrative or sample character associated with another entity, typically used for demonstration or example purposes.
  • C. establishesCharacter
    Indicates that one entity defines, introduces, or sets up the identity or traits of a character in relation to another entity or context.
  • D. supportCharacter
    Indicates that one entity provides assistance, backing, or reinforcement to another entity in performing an action or fulfilling a role.
  • E. allyOfCharacter
    Indicates that one character maintains an alliance or supportive partnership with another character.
  • F. None of above. chosen

Provenance (7 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_69f76ed6df7c8190b018e5baea716ceb completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fbaa19e4a88190b04f26c0d4e708fd completed May 6, 2026, 8:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a40cdb31ebc81908ca3cf583cec06b1 completed June 28, 2026, 7:30 a.m.
NEDg Description generation batch_6a40ce7402cc8190abf4f70571b98544 completed June 28, 2026, 7:34 a.m.
NED2 Entity disambiguation (via description) batch_6a40d066df1481908f66e684e88b8380 completed June 28, 2026, 7:42 a.m.
PD Predicate disambiguation batch_69fba8860f98819080b7bab05837b974 completed May 6, 2026, 8:45 p.m.
PDg Predicate description generation batch_69fbaa108ee48190b84d13df3ef3e365 completed May 6, 2026, 8:52 p.m.
Created at: May 3, 2026, 4:18 p.m.