Triple

T783899
Position Surface form Disambiguated ID Type / Status
Subject Corsica E16558 entity
Predicate hasCity P316 FINISHED
Object Corte
Corte is a historic inland town in central Corsica known for its dramatic citadel and role as a former capital of the island.
 E93039 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: Corte | Statement: [Corsica, hasCity, Corte]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Corte
Context triple: [Corsica, hasCity, Corte]
  • A. La Justice
    La Justice is a philosophical poem by French writer and Nobel laureate Sully Prudhomme that explores themes of law, morality, and the nature of justice.
  • B. New Court
    New Court is a prominent 19th-century neo-Gothic courtyard of St John’s College, Cambridge, overlooking the River Cam and the Bridge of Sighs.
  • C. New Court
    New Court is a prominent 19th-century neo-Gothic courtyard of Trinity College, Cambridge, overlooking the River Cam and known for its grand architecture.
  • D. New Court
    New Court is a prominent quadrangle of Christ's College, Cambridge, known for its historic collegiate architecture and role in housing students and college facilities.
  • E. New Court
    New Court is a prominent quadrangle and set of college buildings at Emmanuel College, Cambridge, known for its historic architecture and role in student life.
  • 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: Corte
Triple: [Corsica, hasCity, Corte]
Generated description
Corte is a historic inland town in central Corsica known for its dramatic citadel and role as a former capital of the island.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Corte
Target entity description: Corte is a historic inland town in central Corsica known for its dramatic citadel and role as a former capital of the island.
  • A. La Justice
    La Justice is a philosophical poem by French writer and Nobel laureate Sully Prudhomme that explores themes of law, morality, and the nature of justice.
  • B. New Court
    New Court is a prominent 19th-century neo-Gothic courtyard of Trinity College, Cambridge, overlooking the River Cam and known for its grand architecture.
  • C. New Court
    New Court is a prominent 19th-century neo-Gothic courtyard of St John’s College, Cambridge, overlooking the River Cam and the Bridge of Sighs.
  • D. New Court
    New Court is a prominent quadrangle and set of college buildings at Emmanuel College, Cambridge, known for its historic architecture and role in student life.
  • E. New Court
    New Court is a prominent quadrangle of Christ's College, Cambridge, known for its historic collegiate architecture and role in housing students and college facilities.
  • 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_69a4936ad1fc81908f190208059ccf78 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a769dc6481908f12e872f997acf3 completed March 1, 2026, 8:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69a6733c2e608190962440d6ef637784 completed March 3, 2026, 5:35 a.m.
NEDg Description generation batch_69a673ccc2308190a887ada146290de8 completed March 3, 2026, 5:38 a.m.
NED2 Entity disambiguation (via description) batch_69a6742d7ba881909385cbc51a2ed7bd completed March 3, 2026, 5:39 a.m.
Created at: March 1, 2026, 7:37 p.m.