Triple

T951689
Position Surface form Disambiguated ID Type / Status
Subject Neath Port Talbot E20536 entity
Predicate contains P35 FINISHED
Object Tonna
Tonna is a village and community in Neath Port Talbot, South Wales, known for its residential character and proximity to the town of Neath.
 E112336 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: Tonna | Statement: [Neath Port Talbot, contains, Tonna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tonna
Context triple: [Neath Port Talbot, contains, Tonna]
  • A. Ammonite
    Ammonite is an extinct Northwest Semitic language once spoken by the ancient Ammonite people in the region of modern-day Jordan.
  • B. Anesidora
    Anesidora is an epithet of the Greek goddess Demeter that emphasizes her role as the giver of gifts, especially the bounty of the earth.
  • C. Sophroniscus
    Sophroniscus was an Athenian stonemason and sculptor best known as the father of the philosopher Socrates.
  • D. Arethusa
    Arethusa is one of the Hesperides, the nymphs of Greek mythology associated with a blissful western garden and its golden apples.
  • E. Marpessa
    Marpessa is a figure in Greek mythology known as a mortal woman whose beauty led to a famous love contest between the god Apollo and the hero Idas.
  • 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: Tonna
Triple: [Neath Port Talbot, contains, Tonna]
Generated description
Tonna is a village and community in Neath Port Talbot, South Wales, known for its residential character and proximity to the town of Neath.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tonna
Target entity description: Tonna is a village and community in Neath Port Talbot, South Wales, known for its residential character and proximity to the town of Neath.
  • A. Ammonite
    Ammonite is an extinct Northwest Semitic language once spoken by the ancient Ammonite people in the region of modern-day Jordan.
  • B. Anesidora
    Anesidora is an epithet of the Greek goddess Demeter that emphasizes her role as the giver of gifts, especially the bounty of the earth.
  • C. Sophroniscus
    Sophroniscus was an Athenian stonemason and sculptor best known as the father of the philosopher Socrates.
  • D. Arethusa
    Arethusa is one of the Hesperides, the nymphs of Greek mythology associated with a blissful western garden and its golden apples.
  • E. Marpessa
    Marpessa is a figure in Greek mythology known as a mortal woman whose beauty led to a famous love contest between the god Apollo and the hero Idas.
  • 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_69a493b0f2fc81908cd227480a5356a1 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b3d757d08190a475cf47febd05ae completed March 1, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69a933ab88b481908298cb855f46540e completed March 5, 2026, 7:41 a.m.
NEDg Description generation batch_69a963a5b8648190b21d9edaf3d053d2 completed March 5, 2026, 11:06 a.m.
NED2 Entity disambiguation (via description) batch_69a9641f3a5c81908894097ab2177c43 completed March 5, 2026, 11:08 a.m.
Created at: March 1, 2026, 7:40 p.m.