Triple

T17035823
Position Surface form Disambiguated ID Type / Status
Subject Donut County E413317 entity
Predicate mainCharacter P1183 FINISHED
Object Mira
Mira is the teenage protagonist of the indie puzzle game Donut County, known for controlling a mysterious hole that swallows up the town.
E1245923 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: Mira | Statement: [Donut County, mainCharacter, Mira]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mira
Context triple: [Donut County, mainCharacter, Mira]
  • A. Mira
    Mira is a small town in northern Ecuador’s Carchi Province, known for its Andean setting and agricultural surroundings.
  • B. Mira
    Mira is a coastal municipality in central Portugal known for its beaches, lagoons, and natural landscapes.
  • C. Mira
    Mira is a town in the Veneto region of northern Italy, situated along the Brenta Canal between Venice and Padua and known for its historic Venetian villas.
  • D. Mira
    Mira is a famous red giant variable star in the constellation Cetus, known for its dramatic changes in brightness over time.
  • E. Mira
    Mira is a 1971 Belgian-Dutch drama film directed by Fons Rademakers, based on Stijn Streuvels’ novel "De Teleurgang van den Waterhoek."
  • 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: Mira
Triple: [Donut County, mainCharacter, Mira]
Generated description
Mira is the teenage protagonist of the indie puzzle game Donut County, known for controlling a mysterious hole that swallows up the town.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mira
Target entity description: Mira is the teenage protagonist of the indie puzzle game Donut County, known for controlling a mysterious hole that swallows up the town.
  • A. Mira
    Mira is the central character in the story "Why Mira Can’t Go Back to Her Old House," around whom the plot’s emotional and narrative conflicts revolve.
  • B. Mira
    Mira is a small town in northern Ecuador’s Carchi Province, known for its Andean setting and agricultural surroundings.
  • C. Mira
    Mira is the courageous female warrior and key protagonist in the historical action film "The Last Legion."
  • D. Mira
    Mira is a coastal municipality in central Portugal known for its beaches, lagoons, and natural landscapes.
  • E. Mira
    Mira is a town in the Veneto region of northern Italy, situated along the Brenta Canal between Venice and Padua and known for its historic Venetian villas.
  • 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_69d886cd18288190b006abab23f811b7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d8f26f50819085dfd0fbecd6394d completed April 18, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b5b71f48190b6c865d57668b5d1 completed May 10, 2026, 11:57 p.m.
NEDg Description generation batch_6a011c2203f0819091a5b4aa7c339585 completed May 11, 2026, midnight
NED2 Entity disambiguation (via description) batch_6a011cc70cb08190b53b6a7402139f93 completed May 11, 2026, 12:03 a.m.
Created at: April 10, 2026, 5:33 a.m.