Triple

T10582571
Position Surface form Disambiguated ID Type / Status
Subject Keres E249771 entity
Predicate nameInGreek P3659 FINISHED
Object Κῆρες
Κῆρες are female death-spirits in Greek mythology associated with violent demise and the carrying off of souls from the battlefield.
E873091 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: Κῆρες | Statement: [Keres, nameInGreek, Κῆρες]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Κῆρες
Context triple: [Keres, nameInGreek, Κῆρες]
  • A. Κρεῖος
    Κρεῖος is the Greek name for Crius, one of the twelve original Titans of Greek mythology associated with the constellations and the heavens.
  • B. Erasinos
    Erasinos is an ancient river in the region of Attica, Greece, historically associated with the sanctuary and coastal area of Brauron.
  • C. Κρηθεύς
    Κρηθεύς is the Greek name for Cretheus, a mythological king of Iolcus in Thessaly and a son of Aeolus in ancient Greek tradition.
  • D. Gytheio
    Gytheio is a historic coastal town and port in the southern Peloponnese of Greece, known as the former seaport of ancient Sparta and a gateway to the Laconian Gulf.
  • E. Kynthos
    Kynthos is an ancient Greek place name, most famously associated with Mount Cynthus on the island of Delos, which gave rise to related personal names such as Kynthia.
  • 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: Κῆρες
Triple: [Keres, nameInGreek, Κῆρες]
Generated description
Κῆρες are female death-spirits in Greek mythology associated with violent demise and the carrying off of souls from the battlefield.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Κῆρες
Target entity description: Κῆρες are female death-spirits in Greek mythology associated with violent demise and the carrying off of souls from the battlefield.
  • A. Κρεῖος
    Κρεῖος is the Greek name for Crius, one of the twelve original Titans of Greek mythology associated with the constellations and the heavens.
  • B. Erasinos
    Erasinos is an ancient river in the region of Attica, Greece, historically associated with the sanctuary and coastal area of Brauron.
  • C. Κρηθεύς
    Κρηθεύς is the Greek name for Cretheus, a mythological king of Iolcus in Thessaly and a son of Aeolus in ancient Greek tradition.
  • D. Gytheio
    Gytheio is a historic coastal town and port in the southern Peloponnese of Greece, known as the former seaport of ancient Sparta and a gateway to the Laconian Gulf.
  • E. Kynthos
    Kynthos is an ancient Greek place name, most famously associated with Mount Cynthus on the island of Delos, which gave rise to related personal names such as Kynthia.
  • 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_69d381c9d3d48190a29ee491e1696a0e completed April 6, 2026, 9:50 a.m.
NER Named-entity recognition batch_69d52766d53c8190b51753768ab58c31 completed April 7, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69d94b78ff28819085acf84418d54733 completed April 10, 2026, 7:11 p.m.
NEDg Description generation batch_69d94d67e16481908efb939a3e65004c completed April 10, 2026, 7:20 p.m.
NED2 Entity disambiguation (via description) batch_69d95227a1f48190ab847606a9ae0500 completed April 10, 2026, 7:40 p.m.
Created at: April 6, 2026, 12:39 p.m.