Triple

T7449212
Position Surface form Disambiguated ID Type / Status
Subject Hylands House E171962 entity
Predicate hasParkland P22590 FINISHED
Object Hylands Park
Hylands Park is a large public park and historic estate grounds in Chelmsford, Essex, known for its expansive green spaces, events, and surrounding Hylands House.
E665938 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: Hylands Park | Statement: [Hylands House, hasParkland, Hylands Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hylands Park
Context triple: [Hylands House, hasParkland, Hylands Park]
  • A. Keilor Park
    Keilor Park is a residential and industrial suburb in Melbourne, Victoria, Australia, located near Tullamarine Airport.
  • B. Oakleigh Park
    Oakleigh Park is a suburban residential area in north London known for its quiet streets, green spaces, and commuter rail links into central London.
  • C. Belmore Park
    Belmore Park is a central public park in Goulburn, New South Wales, known for its historic features, gardens, and role as a key community gathering space.
  • D. Sansom Park
    Sansom Park is a small city located in Tarrant County, Texas, within the Dallas–Fort Worth metropolitan area.
  • E. Howard Park
    Howard Park is a prominent public park and recreational area in South Bend, Indiana, known for its riverfront setting and community amenities.
  • 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: Hylands Park
Triple: [Hylands House, hasParkland, Hylands Park]
Generated description
Hylands Park is a large public park and historic estate grounds in Chelmsford, Essex, known for its expansive green spaces, events, and surrounding Hylands House.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hylands Park
Target entity description: Hylands Park is a large public park and historic estate grounds in Chelmsford, Essex, known for its expansive green spaces, events, and surrounding Hylands House.
  • A. Keilor Park
    Keilor Park is a residential and industrial suburb in Melbourne, Victoria, Australia, located near Tullamarine Airport.
  • B. Oakleigh Park
    Oakleigh Park is a suburban residential area in north London known for its quiet streets, green spaces, and commuter rail links into central London.
  • C. Belmore Park
    Belmore Park is a central public park in Goulburn, New South Wales, known for its historic features, gardens, and role as a key community gathering space.
  • D. Sansom Park
    Sansom Park is a small city located in Tarrant County, Texas, within the Dallas–Fort Worth metropolitan area.
  • E. Howard Park
    Howard Park is a prominent public park and recreational area in South Bend, Indiana, known for its riverfront setting and community amenities.
  • 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_69c68a65402881908f7869368eb746fb completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f389ddd48190a4b8753c67220c4f completed March 27, 2026, 9:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c827b0e9848190b28ff10b12b10a33 completed March 28, 2026, 7:10 p.m.
NEDg Description generation batch_69c8299bb8c08190a5a78b0c1a8cc0fb completed March 28, 2026, 7:18 p.m.
NED2 Entity disambiguation (via description) batch_69c82ad4384481909616bdfd02624a48 completed March 28, 2026, 7:24 p.m.
Created at: March 27, 2026, 3:14 p.m.