Triple

T9683439
Position Surface form Disambiguated ID Type / Status
Subject Charolles E234344 entity
Predicate locatedOnRiver P165 FINISHED
Object Semence
The Semence is a river in eastern France that flows through the commune of Charolles in the Saône-et-Loire department.
E814745 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: Semence | Statement: [Charolles, locatedOnRiver, Semence]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Semence
Context triple: [Charolles, locatedOnRiver, Semence]
  • A. Seedley
    Seedley is a residential district within the city of Salford in Greater Manchester, England.
  • B. Tuff Seed
    "Tuff Seed" is a popular reggae/dancehall track by Ghanaian artist Stonebwoy that helped solidify his international recognition.
  • C. Semín
    Semín is a small village in the Pardubice Region of the Czech Republic, known as the birthplace of architect Josef Gočár.
  • D. Piantas
    Piantas are a race of tall, palm tree–like humanoid inhabitants of Isle Delfino in the Super Mario series, best known for their prominent role in Super Mario Sunshine.
  • E. SEED
    SEED is a Stanford University institute focused on promoting innovation and entrepreneurship to drive economic development in emerging and developing economies.
  • 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: Semence
Triple: [Charolles, locatedOnRiver, Semence]
Generated description
The Semence is a river in eastern France that flows through the commune of Charolles in the Saône-et-Loire department.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Semence
Target entity description: The Semence is a river in eastern France that flows through the commune of Charolles in the Saône-et-Loire department.
  • A. Seedley
    Seedley is a residential district within the city of Salford in Greater Manchester, England.
  • B. Tuff Seed
    "Tuff Seed" is a popular reggae/dancehall track by Ghanaian artist Stonebwoy that helped solidify his international recognition.
  • C. Semín
    Semín is a small village in the Pardubice Region of the Czech Republic, known as the birthplace of architect Josef Gočár.
  • D. Piantas
    Piantas are a race of tall, palm tree–like humanoid inhabitants of Isle Delfino in the Super Mario series, best known for their prominent role in Super Mario Sunshine.
  • E. SEED
    SEED is a Stanford University institute focused on promoting innovation and entrepreneurship to drive economic development in emerging and developing economies.
  • 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_69ca84c99e34819092e5563a7106cfca completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9ccf21a08190a1302b933b9e50be completed April 1, 2026, 10:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1910192e88190b10409ae62c1c948 completed April 4, 2026, 10:30 p.m.
NEDg Description generation batch_69d19327f0b481908be85bcb0deccb46 completed April 4, 2026, 10:39 p.m.
NED2 Entity disambiguation (via description) batch_69d193fac390819092dd913dc78e2841 completed April 4, 2026, 10:43 p.m.
Created at: March 30, 2026, 8:16 p.m.