Triple

T4837704
Position Surface form Disambiguated ID Type / Status
Subject Akhmim E108101 entity
Predicate majorDeityVenerated P7648 FINISHED
Object Repyt
Repyt is an ancient Egyptian lioness goddess primarily worshipped at Akhmim, associated with protection and sometimes linked to solar and warlike aspects.
 E475405 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: Repyt | Statement: [Akhmim, majorDeityVenerated, Repyt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Repyt
Context triple: [Akhmim, majorDeityVenerated, Repyt]
  • A. Pym
    Pym is an English surname most notably associated with John Pym, a leading parliamentary figure in the early stages of the English Civil War.
  • B. Pyr
    Pyr is a science fiction and fantasy publishing imprint known for releasing speculative fiction titles under the Prometheus Books umbrella.
  • C. Vyper
    Vyper is a Pythonic, security-focused programming language used to write smart contracts on the Ethereum blockchain.
  • D. Telepylus
    Telepylus is the mythological city in Homer’s Odyssey that serves as the homeland of the man-eating giant Laestrygonians.
  • E. Pythonidae
    Pythonidae is a family of nonvenomous constrictor snakes that includes pythons found across Africa, Asia, and Australia.
  • 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: Repyt
Triple: [Akhmim, majorDeityVenerated, Repyt]
Generated description
Repyt is an ancient Egyptian lioness goddess primarily worshipped at Akhmim, associated with protection and sometimes linked to solar and warlike aspects.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Repyt
Target entity description: Repyt is an ancient Egyptian lioness goddess primarily worshipped at Akhmim, associated with protection and sometimes linked to solar and warlike aspects.
  • A. Pym
    Pym is an English surname most notably associated with John Pym, a leading parliamentary figure in the early stages of the English Civil War.
  • B. Pyr
    Pyr is a science fiction and fantasy publishing imprint known for releasing speculative fiction titles under the Prometheus Books umbrella.
  • C. Vyper
    Vyper is a Pythonic, security-focused programming language used to write smart contracts on the Ethereum blockchain.
  • D. Telepylus
    Telepylus is the mythological city in Homer’s Odyssey that serves as the homeland of the man-eating giant Laestrygonians.
  • E. Pythonidae
    Pythonidae is a family of nonvenomous constrictor snakes that includes pythons found across Africa, Asia, and Australia.
  • 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_69bd43fbe444819085cb970706ef73f7 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6ce2e810819089f9a3f2a7574d44 completed March 20, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69be5cc054ac819099d6d3dbf415e710 completed March 21, 2026, 8:54 a.m.
NEDg Description generation batch_69be60d4fa0c8190b6d197eb3dbafff7 completed March 21, 2026, 9:11 a.m.
NED2 Entity disambiguation (via description) batch_69be61789d388190bc23d7f44cee2e5d completed March 21, 2026, 9:14 a.m.
Created at: March 20, 2026, 1:25 p.m.