Triple

T7432479
Position Surface form Disambiguated ID Type / Status
Subject York city walls E171524 entity
Predicate hasPart P35 FINISHED
Object Tower Ninety-eight
Tower Ninety-eight is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
E691810 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: Tower Ninety-eight | Statement: [York city walls, hasPart, Tower Ninety-eight]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tower Ninety-eight
Context triple: [York city walls, hasPart, Tower Ninety-eight]
  • A. Tower Ninety
    Tower Ninety is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
  • B. Tower Ninety-seven
    Tower Ninety-seven is one of the medieval defensive towers incorporated into the historic York city walls in York, England.
  • C. Tower Ninety-six
    Tower Ninety-six is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
  • D. Tower Ninety-five
    Tower Ninety-five is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
  • E. Tower Ninety-two
    Tower Ninety-two is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
  • 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: Tower Ninety-eight
Triple: [York city walls, hasPart, Tower Ninety-eight]
Generated description
Tower Ninety-eight is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tower Ninety-eight
Target entity description: Tower Ninety-eight is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
  • A. Tower Ninety
    Tower Ninety is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
  • B. Tower Ninety-seven
    Tower Ninety-seven is one of the medieval defensive towers incorporated into the historic York city walls in York, England.
  • C. Tower Ninety-six
    Tower Ninety-six is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
  • D. Tower Ninety-five
    Tower Ninety-five is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
  • E. Tower Ninety-two
    Tower Ninety-two is one of the numbered defensive towers incorporated into the historic medieval city walls of York, England.
  • 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_69c68a63491881909281f73d4d5643bf completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f325ea908190b668fd4ce646f1e6 completed March 27, 2026, 9:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69c9abd319048190a24be5112c810489 completed March 29, 2026, 10:46 p.m.
NEDg Description generation batch_69c9b01b23048190a4805947dd403cd8 completed March 29, 2026, 11:04 p.m.
NED2 Entity disambiguation (via description) batch_69c9b080ab4c8190a8d69dc9fee80510 completed March 29, 2026, 11:06 p.m.
Created at: March 27, 2026, 3:12 p.m.