Triple

T156954
Position Surface form Disambiguated ID Type / Status
Subject Ancient Greek religion E3200 entity
Predicate hasMythologicalFigure P1183 FINISHED
Object Orpheus
Orpheus is a legendary musician, poet, and prophet in ancient Greek mythology, famed for his enchanting music that could charm all living things and even the gods of the underworld.
 E31875 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: Orpheus | Statement: [Ancient Greek religion, hasMythologicalFigure, Orpheus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Orpheus
Context triple: [Ancient Greek religion, hasMythologicalFigure, Orpheus]
  • A. Sterope
    Sterope is a figure from Greek mythology, traditionally considered one of the Pleiades and a daughter of the Titan Atlas.
  • B. Dionysus
    Dionysus is the ancient Greek god of wine, ecstasy, theater, and ritual madness, often linked to mystery cults and ecstatic worship.
  • C. Semele
    Semele is a mortal princess in Greek mythology, best known as the mother of Dionysus by Zeus and for her tragic death upon seeing his divine form.
  • D. Perseus
    Perseus is a legendary Greek hero famed for slaying the Gorgon Medusa and rescuing Andromeda.
  • E. Oberon
    Oberon is a modular, type-safe systems programming language designed by Niklaus Wirth as a streamlined successor to Pascal and Modula-2, emphasizing simplicity and efficiency.
  • 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: Orpheus
Triple: [Ancient Greek religion, hasMythologicalFigure, Orpheus]
Generated description
Orpheus is a legendary musician, poet, and prophet in ancient Greek mythology, famed for his enchanting music that could charm all living things and even the gods of the underworld.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Orpheus
Target entity description: Orpheus is a legendary musician, poet, and prophet in ancient Greek mythology, famed for his enchanting music that could charm all living things and even the gods of the underworld.
  • A. Sterope
    Sterope is a figure from Greek mythology, traditionally considered one of the Pleiades and a daughter of the Titan Atlas.
  • B. Dionysus
    Dionysus is the ancient Greek god of wine, ecstasy, theater, and ritual madness, often linked to mystery cults and ecstatic worship.
  • C. Semele
    Semele is a mortal princess in Greek mythology, best known as the mother of Dionysus by Zeus and for her tragic death upon seeing his divine form.
  • D. Perseus
    Perseus is a legendary Greek hero famed for slaying the Gorgon Medusa and rescuing Andromeda.
  • E. Oberon
    Oberon is a modular, type-safe systems programming language designed by Niklaus Wirth as a streamlined successor to Pascal and Modula-2, emphasizing simplicity and efficiency.
  • 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_69a2527757ec819090b8becb2cf1a862 completed Feb. 28, 2026, 2:27 a.m.
NER Named-entity recognition batch_69a25bac998c819099f2bed899220a78 completed Feb. 28, 2026, 3:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69a36ceb0244819092fdbbd095804b83 completed Feb. 28, 2026, 10:32 p.m.
NEDg Description generation batch_69a36d44f0e881909c1e96cb2c217ece completed Feb. 28, 2026, 10:33 p.m.
NED2 Entity disambiguation (via description) batch_69a36e7310ec8190a688b29338306cec completed Feb. 28, 2026, 10:38 p.m.
Created at: Feb. 28, 2026, 2:31 a.m.