Triple

T5453139
Position Surface form Disambiguated ID Type / Status
Subject Abellio E122414 entity
Predicate namedAfter P63 FINISHED
Object Abellio (Celtic deity)
Abellio (Celtic deity) is a little-known god from ancient Gaulish religion, likely associated with the sun, apple trees, or orchards, and venerated in the region of the Pyrenees.
 E520718 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: Abellio (Celtic deity) | Statement: [Abellio, namedAfter, Abellio (Celtic deity)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Abellio (Celtic deity)
Context triple: [Abellio, namedAfter, Abellio (Celtic deity)]
  • A. Alba
    Alba is the Gaelic name for the early medieval kingdom that evolved into the nation of Scotland.
  • B. Alba
    Alba is a prominent Spanish noble house historically associated with the powerful Dukes of Alba.
  • C. Alba
    Alba is a historic town in Italy’s Piedmont region, renowned for its white truffles, fine wines, and medieval architecture.
  • D. Abella
    Abella is an interactive theorem prover and proof assistant designed for reasoning about relational specifications, particularly those involving higher-order abstract syntax and inductive and coinductive definitions.
  • E. Abella
    Abella was an ancient town in Campania, Italy, known from Roman-era inscriptions and archaeological remains.
  • 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: Abellio (Celtic deity)
Triple: [Abellio, namedAfter, Abellio (Celtic deity)]
Generated description
Abellio (Celtic deity) is a little-known god from ancient Gaulish religion, likely associated with the sun, apple trees, or orchards, and venerated in the region of the Pyrenees.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Abellio (Celtic deity)
Target entity description: Abellio (Celtic deity) is a little-known god from ancient Gaulish religion, likely associated with the sun, apple trees, or orchards, and venerated in the region of the Pyrenees.
  • A. Alba
    Alba is the Gaelic name for the early medieval kingdom that evolved into the nation of Scotland.
  • B. Alba
    Alba is a prominent Spanish noble house historically associated with the powerful Dukes of Alba.
  • C. Alba
    Alba is a historic town in Italy’s Piedmont region, renowned for its white truffles, fine wines, and medieval architecture.
  • D. Abella
    Abella is an interactive theorem prover and proof assistant designed for reasoning about relational specifications, particularly those involving higher-order abstract syntax and inductive and coinductive definitions.
  • E. Abella
    Abella was an ancient town in Campania, Italy, known from Roman-era inscriptions and archaeological remains.
  • 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_69bd46424248819085282ddf50a565f3 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd91e170f48190b47419b5e2ff71a4 completed March 20, 2026, 6:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf4140248081908c7f42b91579a837 completed March 22, 2026, 1:09 a.m.
NEDg Description generation batch_69bf41dd96448190973b7241df5dbb24 completed March 22, 2026, 1:11 a.m.
NED2 Entity disambiguation (via description) batch_69bf42b97d40819087a98c1cc58bb964 completed March 22, 2026, 1:15 a.m.
Created at: March 20, 2026, 2:08 p.m.