Triple

T3761589
Position Surface form Disambiguated ID Type / Status
Subject Ludlow E82172 entity
Predicate hasLandmark P105 FINISHED
Object Buttercross
Buttercross is a historic market building in the center of Ludlow, England, known for its distinctive architecture and role in the town’s traditional trading activities.
E386594 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: Buttercross | Statement: [Ludlow, hasLandmark, Buttercross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Buttercross
Context triple: [Ludlow, hasLandmark, Buttercross]
  • A. Whitecross
    Whitecross is a small locality in Northern Ireland known for its proximity to the site of the Kingsmill massacre during the Troubles.
  • B. Achterhooks
    Achterhooks is a regional Low Saxon dialect spoken in the Achterhoek area of the eastern Netherlands.
  • C. Corkscrew
    Corkscrew is a steel roller coaster at Michigan’s Adventure known for its signature double-inversion corkscrew elements.
  • D. Mankas Corner
    Mankas Corner is a small unincorporated community and historic rural crossroads located in Solano County, California.
  • E. Leatherhead
    Leatherhead is a historic market town in the county of Surrey in South East England, situated on the River Mole and serving as a local commercial and commuter hub.
  • 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: Buttercross
Triple: [Ludlow, hasLandmark, Buttercross]
Generated description
Buttercross is a historic market building in the center of Ludlow, England, known for its distinctive architecture and role in the town’s traditional trading activities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Buttercross
Target entity description: Buttercross is a historic market building in the center of Ludlow, England, known for its distinctive architecture and role in the town’s traditional trading activities.
  • A. Whitecross
    Whitecross is a small locality in Northern Ireland known for its proximity to the site of the Kingsmill massacre during the Troubles.
  • B. Achterhooks
    Achterhooks is a regional Low Saxon dialect spoken in the Achterhoek area of the eastern Netherlands.
  • C. Corkscrew
    Corkscrew is a steel roller coaster at Michigan’s Adventure known for its signature double-inversion corkscrew elements.
  • D. Mankas Corner
    Mankas Corner is a small unincorporated community and historic rural crossroads located in Solano County, California.
  • E. Leatherhead
    Leatherhead is a historic market town in the county of Surrey in South East England, situated on the River Mole and serving as a local commercial and commuter hub.
  • 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_69ad8b1db40081908b61ffa6b78afd4d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcbc553a08190ba361675901496ed completed March 8, 2026, 7:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4e51acd0c81909a675e525ece6d1b completed March 14, 2026, 4:33 a.m.
NEDg Description generation batch_69b4e8d7b6d48190a56c3d1921bb2088 completed March 14, 2026, 4:49 a.m.
NED2 Entity disambiguation (via description) batch_69b4e966a5648190a449fbb23c39f905 completed March 14, 2026, 4:51 a.m.
Created at: March 8, 2026, 3:35 p.m.