Triple

T13276472
Position Surface form Disambiguated ID Type / Status
Subject Maesteg railway station E316202 entity
Predicate hasServiceTo P6787 FINISHED
Object Tondu
Tondu is a village in Bridgend County Borough, South Wales, historically known for its coal mining and ironworks industries.
E1031773 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: Tondu | Statement: [Maesteg railway station, hasServiceTo, Tondu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tondu
Context triple: [Maesteg railway station, hasServiceTo, Tondu]
  • A. Toffia
    Toffia is a small historic hilltop town in the Lazio region of central Italy, known for its medieval architecture and scenic countryside setting.
  • B. Tozzer
    Tozzer is a surname most notably associated with Alfred Marston Tozzer, an American anthropologist and archaeologist known for his pioneering work on Mayan civilization.
  • C. Tupe
    Tupe is a small Andean town in Peru known for preserving the unique Jaqaru indigenous language and culture.
  • D. Tinetto
    Tinetto is a small rocky island off the Ligurian coast of Italy, near La Spezia, known for its natural beauty and historical monastic ruins.
  • E. Tannat
    Tannat is a robust, tannin-rich red wine grape variety traditionally associated with southwestern France and now also widely grown in Uruguay and other New World regions.
  • 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: Tondu
Triple: [Maesteg railway station, hasServiceTo, Tondu]
Generated description
Tondu is a village in Bridgend County Borough, South Wales, historically known for its coal mining and ironworks industries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tondu
Target entity description: Tondu is a village in Bridgend County Borough, South Wales, historically known for its coal mining and ironworks industries.
  • A. Toffia
    Toffia is a small historic hilltop town in the Lazio region of central Italy, known for its medieval architecture and scenic countryside setting.
  • B. Tozzer
    Tozzer is a surname most notably associated with Alfred Marston Tozzer, an American anthropologist and archaeologist known for his pioneering work on Mayan civilization.
  • C. Tupe
    Tupe is a small Andean town in Peru known for preserving the unique Jaqaru indigenous language and culture.
  • D. Tinetto
    Tinetto is a small rocky island off the Ligurian coast of Italy, near La Spezia, known for its natural beauty and historical monastic ruins.
  • E. Tannat
    Tannat is a robust, tannin-rich red wine grape variety traditionally associated with southwestern France and now also widely grown in Uruguay and other New World regions.
  • 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_69d806b349908190a9a61dd9323bf153 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d99042f56c819082440c89c0adc442 completed April 11, 2026, 12:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69f70a54ff488190a759b46963c0d842 completed May 3, 2026, 8:41 a.m.
NEDg Description generation batch_69f713088cc48190b705336339527f46 completed May 3, 2026, 9:19 a.m.
NED2 Entity disambiguation (via description) batch_69f713bd94048190a61dbd955bd1c542 completed May 3, 2026, 9:22 a.m.
Created at: April 9, 2026, 9:26 p.m.