Triple

T989438
Position Surface form Disambiguated ID Type / Status
Subject Cupar E21353 entity
Predicate hasPostTown P2711 FINISHED
Object CUPAR
CUPAR is a historic market town in Fife, Scotland, known for its traditional architecture and role as a local administrative and commercial center.
E117621 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: CUPAR | Statement: [Cupar, hasPostTown, CUPAR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CUPAR
Context triple: [Cupar, hasPostTown, CUPAR]
  • A. CUP
    CUP is an academic publishing organization associated with York University, known for producing scholarly books and journals.
  • B. The Cup
    The Cup is a common nickname for the Stanley Cup, the championship trophy awarded annually to the National Hockey League playoff winner and one of the most iconic prizes in professional sports.
  • C. Carris
    Carris is the main public transport company in Lisbon, Portugal, operating the city's buses, trams, and certain historic lifts.
  • D. Caterham
    Caterham is a town in the Tandridge district of Surrey, England, known as a commuter settlement on the edge of the London metropolitan area.
  • E. Tartan Racing
    Tartan Racing is an autonomous vehicle research team formed by Carnegie Mellon University and General Motors that gained prominence by winning the 2007 DARPA Urban Challenge.
  • 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: CUPAR
Triple: [Cupar, hasPostTown, CUPAR]
Generated description
CUPAR is a historic market town in Fife, Scotland, known for its traditional architecture and role as a local administrative and commercial center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: CUPAR
Target entity description: CUPAR is a historic market town in Fife, Scotland, known for its traditional architecture and role as a local administrative and commercial center.
  • A. CUP
    CUP is an academic publishing organization associated with York University, known for producing scholarly books and journals.
  • B. The Cup
    The Cup is a common nickname for the Stanley Cup, the championship trophy awarded annually to the National Hockey League playoff winner and one of the most iconic prizes in professional sports.
  • C. Carris
    Carris is the main public transport company in Lisbon, Portugal, operating the city's buses, trams, and certain historic lifts.
  • D. Caterham
    Caterham is a town in the Tandridge district of Surrey, England, known as a commuter settlement on the edge of the London metropolitan area.
  • E. Tartan Racing
    Tartan Racing is an autonomous vehicle research team formed by Carnegie Mellon University and General Motors that gained prominence by winning the 2007 DARPA Urban Challenge.
  • 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_69a493c383dc8190a03257f22d4b4183 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b4aa16f081909dcc7a7ce3fb1b64 completed March 1, 2026, 9:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac258d9f4c8190b285455410b30575 completed March 7, 2026, 1:18 p.m.
NEDg Description generation batch_69ac267e4fa08190895fa6809d0decb8 completed March 7, 2026, 1:22 p.m.
NED2 Entity disambiguation (via description) batch_69ac271c8ad081909c1f1629e0793c40 completed March 7, 2026, 1:24 p.m.
Created at: March 1, 2026, 7:41 p.m.