Triple

T18901563
Position Surface form Disambiguated ID Type / Status
Subject Four Lands E462351 entity
Predicate hasRegion P285 FINISHED
Object Westland
Westland is a fictional region within the Four Lands setting, often depicted as a distinct realm with its own landscapes, peoples, and cultures.
 E1348078 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: Westland | Statement: [Four Lands, hasRegion, Westland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Westland
Context triple: [Four Lands, hasRegion, Westland]
  • A. Westland
    Westland is a municipality in the Dutch province of South Holland known for its extensive greenhouse horticulture and flower production.
  • B. Westland
    Westland is a suburban city in southeastern Michigan, United States, known as part of the Detroit metropolitan area.
  • C. Haseldine
    Haseldine is the middle name of William Haseldine Pepys, an English scientist and instrument maker active in the late 18th and early 19th centuries.
  • D. Kersey
    Kersey is a historic village in Suffolk, England, noted for its picturesque medieval buildings and traditional rural character.
  • E. Whifflet
    Whifflet is a district in Coatbridge, North Lanarkshire, Scotland, known historically for its industrial heritage and railway connections.
  • 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: Westland
Triple: [Four Lands, hasRegion, Westland]
Generated description
Westland is a fictional region within the Four Lands setting, often depicted as a distinct realm with its own landscapes, peoples, and cultures.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Westland
Target entity description: Westland is a fictional region within the Four Lands setting, often depicted as a distinct realm with its own landscapes, peoples, and cultures.
  • A. Westland
    Westland is a municipality in the Dutch province of South Holland known for its extensive greenhouse horticulture and flower production.
  • B. Westland
    Westland is a suburban city in southeastern Michigan, United States, known as part of the Detroit metropolitan area.
  • C. Haseldine
    Haseldine is the middle name of William Haseldine Pepys, an English scientist and instrument maker active in the late 18th and early 19th centuries.
  • D. Kersey
    Kersey is a historic village in Suffolk, England, noted for its picturesque medieval buildings and traditional rural character.
  • E. Whifflet
    Whifflet is a district in Coatbridge, North Lanarkshire, Scotland, known historically for its industrial heritage and railway connections.
  • 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_69d8dcfd05bc819088903cca13cc2846 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c52954bc8190a237627c09615ac1 completed April 20, 2026, 6:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0582bc878c8190bfb5f058aa272225 completed May 14, 2026, 8:07 a.m.
NEDg Description generation batch_6a05871baa5881908c3c0f407b2d82c0 completed May 14, 2026, 8:26 a.m.
NED2 Entity disambiguation (via description) batch_6a0587acbf1c819088bae20aa89783eb completed May 14, 2026, 8:28 a.m.
Created at: April 10, 2026, 11:58 a.m.