Triple

T2282405
Position Surface form Disambiguated ID Type / Status
Subject Nyx E51309 entity
Predicate parentOf P120 FINISHED
Object Keres
Keres are female death-spirits from Greek mythology associated with violent death and the battlefield, often depicted as dark, bloodthirsty beings who seize the souls of the dying.
 E249771 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: Keres | Statement: [Nyx, parentOf, Keres]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Keres
Context triple: [Nyx, parentOf, Keres]
  • A. Kezlev
    Kezlev is the historical Crimean Tatar name for the city now known as Eupatoria, a coastal town on the western shore of Crimea.
  • B. Kenderes
    Kenderes is a town in Hungary best known as the birthplace and family estate center of Regent Miklós Horthy.
  • C. Kierling
    Kierling is a small locality in Lower Austria best known as the place where writer Franz Kafka spent his final days and died.
  • D. Kamen
    Kamen is a surname most prominently associated with American inventor and entrepreneur Dean Kamen, known for creating the Segway and numerous medical devices.
  • E. Kerria
    Kerria is a small genus of deciduous flowering shrubs, best known for the ornamental Japanese kerria with its bright yellow, rose-like blooms.
  • 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: Keres
Triple: [Nyx, parentOf, Keres]
Generated description
Keres are female death-spirits from Greek mythology associated with violent death and the battlefield, often depicted as dark, bloodthirsty beings who seize the souls of the dying.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Keres
Target entity description: Keres are female death-spirits from Greek mythology associated with violent death and the battlefield, often depicted as dark, bloodthirsty beings who seize the souls of the dying.
  • A. Kezlev
    Kezlev is the historical Crimean Tatar name for the city now known as Eupatoria, a coastal town on the western shore of Crimea.
  • B. Kenderes
    Kenderes is a town in Hungary best known as the birthplace and family estate center of Regent Miklós Horthy.
  • C. Kierling
    Kierling is a small locality in Lower Austria best known as the place where writer Franz Kafka spent his final days and died.
  • D. Kamen
    Kamen is a surname most prominently associated with American inventor and entrepreneur Dean Kamen, known for creating the Segway and numerous medical devices.
  • E. Kerria
    Kerria is a small genus of deciduous flowering shrubs, best known for the ornamental Japanese kerria with its bright yellow, rose-like blooms.
  • 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_69a88b08e4308190bdac9aebcca1c91a completed March 4, 2026, 7:42 p.m.
NER Named-entity recognition batch_69abc21d6d748190980128c1bc5b9621 completed March 7, 2026, 6:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae71e7b44c8190ab647646352b71b7 completed March 9, 2026, 7:08 a.m.
NEDg Description generation batch_69ae72bf22088190a2c111a71eb0dda7 completed March 9, 2026, 7:11 a.m.
NED2 Entity disambiguation (via description) batch_69ae731ab8bc819090fac5b311cb5fe0 completed March 9, 2026, 7:13 a.m.
Created at: March 4, 2026, 7:48 p.m.