Triple

T4730167
Position Surface form Disambiguated ID Type / Status
Subject Mansfield E104984 entity
Predicate footballClubStadium P890 FINISHED
Object Field Mill
Field Mill is a historic football stadium in Mansfield, England, serving as the long-time home ground of Mansfield Town FC.
E465135 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: Field Mill | Statement: [Mansfield, footballClubStadium, Field Mill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Field Mill
Context triple: [Mansfield, footballClubStadium, Field Mill]
  • A. Fielden
    Fielden is an English surname historically associated with figures involved in labor activism and social reform.
  • B. Ifield
    Ifield is a residential neighbourhood and historic village area within the town of Crawley in West Sussex, England.
  • C. Ravenshead
    Ravenshead is a village in Nottinghamshire, England, known for its proximity to the historic Newstead Abbey, former home of poet Lord Byron.
  • D. Hilly Fields
    Hilly Fields is a public park and green open space in the London Borough of Lewisham, known for its panoramic city views and recreational facilities.
  • E. Martlesham Heath
    Martlesham Heath is a village and residential area in Suffolk, England, known for its planned development and historical links to aviation and telecommunications research.
  • 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: Field Mill
Triple: [Mansfield, footballClubStadium, Field Mill]
Generated description
Field Mill is a historic football stadium in Mansfield, England, serving as the long-time home ground of Mansfield Town FC.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Field Mill
Target entity description: Field Mill is a historic football stadium in Mansfield, England, serving as the long-time home ground of Mansfield Town FC.
  • A. Fielden
    Fielden is an English surname historically associated with figures involved in labor activism and social reform.
  • B. Ifield
    Ifield is a residential neighbourhood and historic village area within the town of Crawley in West Sussex, England.
  • C. Ravenshead
    Ravenshead is a village in Nottinghamshire, England, known for its proximity to the historic Newstead Abbey, former home of poet Lord Byron.
  • D. Hilly Fields
    Hilly Fields is a public park and green open space in the London Borough of Lewisham, known for its panoramic city views and recreational facilities.
  • E. Martlesham Heath
    Martlesham Heath is a village and residential area in Suffolk, England, known for its planned development and historical links to aviation and telecommunications research.
  • 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_69bd43ee52048190b81a4f066534ffb3 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd64629bc081908754aa8a2630091f completed March 20, 2026, 3:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69be10a4bc0481908935278afb13503d completed March 21, 2026, 3:29 a.m.
NEDg Description generation batch_69be13d99f9881908dd19dd40ac87a6d completed March 21, 2026, 3:43 a.m.
NED2 Entity disambiguation (via description) batch_69be143ea2108190941294255bc4679c completed March 21, 2026, 3:45 a.m.
Created at: March 20, 2026, 1:19 p.m.