Triple

T2561796
Position Surface form Disambiguated ID Type / Status
Subject Sebastian E57255 entity
Predicate hasVariant P455 FINISHED
Object Basti
Basti is a common German diminutive form of the given name Sebastian.
E277386 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: Basti | Statement: [Sebastian, hasVariant, Basti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Basti
Context triple: [Sebastian, hasVariant, Basti]
  • A. Bisha
    Bisha is a major inland city in southwestern Saudi Arabia known for its agricultural production and strategic location within the Asir region.
  • B. Ain Sokhna
    Ain Sokhna is a popular Egyptian Red Sea resort town known for its beaches, proximity to Cairo, and role as a growing industrial and port area.
  • C. Batha
    Batha is a central region of Chad known for its semi-arid Sahelian landscape and traditional pastoralist communities.
  • D. Dender
    The Dender is a river in Belgium that flows through Wallonia and Flanders before joining the Scheldt near the city of Dendermonde.
  • E. Faras
    Faras was an important ancient city in Nubia, known especially for its Christian-era cathedral and remarkable wall paintings discovered during archaeological excavations.
  • 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: Basti
Triple: [Sebastian, hasVariant, Basti]
Generated description
Basti is a common German diminutive form of the given name Sebastian.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Basti
Target entity description: Basti is a common German diminutive form of the given name Sebastian.
  • A. Bisha
    Bisha is a major inland city in southwestern Saudi Arabia known for its agricultural production and strategic location within the Asir region.
  • B. Ain Sokhna
    Ain Sokhna is a popular Egyptian Red Sea resort town known for its beaches, proximity to Cairo, and role as a growing industrial and port area.
  • C. Batha
    Batha is a central region of Chad known for its semi-arid Sahelian landscape and traditional pastoralist communities.
  • D. Dender
    The Dender is a river in Belgium that flows through Wallonia and Flanders before joining the Scheldt near the city of Dendermonde.
  • E. Faras
    Faras was an important ancient city in Nubia, known especially for its Christian-era cathedral and remarkable wall paintings discovered during archaeological excavations.
  • 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_69ab4a4ef9008190a0e6d4422b9418b7 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd336183c819084ed7de8ccc4c548 completed March 7, 2026, 7:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69af5d264db481908e9dc3b5e2e8260a completed March 9, 2026, 11:52 p.m.
NEDg Description generation batch_69af5dc8aca48190b359526bf60f79ce completed March 9, 2026, 11:54 p.m.
NED2 Entity disambiguation (via description) batch_69af5e781360819080b4b96942beb17d completed March 9, 2026, 11:57 p.m.
Created at: March 6, 2026, 9:48 p.m.