Triple

T19029572
Position Surface form Disambiguated ID Type / Status
Subject Gisborne wine region E465698 entity
Predicate hasSubregion P285 FINISHED
Object Manutuke
Manutuke is a subregion of New Zealand’s Gisborne wine area, known for its viticulture and wine production.
E1354720 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: Manutuke | Statement: [Gisborne wine region, hasSubregion, Manutuke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manutuke
Context triple: [Gisborne wine region, hasSubregion, Manutuke]
  • A. Maskun
    Maskun was an Indonesian politician associated with the nationalist movement and the Indonesian National Party.
  • B. Mankessim
    Mankessim is a major commercial and historical town in Ghana known as an important market center and traditional seat of the Fante people.
  • C. Mansaka
    Mansaka is an Austronesian language spoken by the indigenous Mansaka people of southeastern Mindanao in the Philippines.
  • D. Tettamanzi
    Tettamanzi is an Italian surname most notably associated with Cardinal Dionigi Tettamanzi, a prominent figure in the Roman Catholic Church.
  • E. Mantena
    Mantena is a Norwegian company that specializes in the maintenance and servicing of railway rolling stock and related rail infrastructure.
  • 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: Manutuke
Triple: [Gisborne wine region, hasSubregion, Manutuke]
Generated description
Manutuke is a subregion of New Zealand’s Gisborne wine area, known for its viticulture and wine production.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Manutuke
Target entity description: Manutuke is a subregion of New Zealand’s Gisborne wine area, known for its viticulture and wine production.
  • A. Maskun
    Maskun was an Indonesian politician associated with the nationalist movement and the Indonesian National Party.
  • B. Mankessim
    Mankessim is a major commercial and historical town in Ghana known as an important market center and traditional seat of the Fante people.
  • C. Mansaka
    Mansaka is an Austronesian language spoken by the indigenous Mansaka people of southeastern Mindanao in the Philippines.
  • D. Tettamanzi
    Tettamanzi is an Italian surname most notably associated with Cardinal Dionigi Tettamanzi, a prominent figure in the Roman Catholic Church.
  • E. Mantena
    Mantena is a Norwegian company that specializes in the maintenance and servicing of railway rolling stock and related rail infrastructure.
  • 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_69d8dd0359648190bc2a9202c5cf29d2 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d73f98dc81909acbb366f00d2d54 completed April 20, 2026, 7:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05be59f0088190ae133c2d12beb2c0 completed May 14, 2026, 12:21 p.m.
NEDg Description generation batch_6a05bf20c800819084e54a34574cb630 completed May 14, 2026, 12:25 p.m.
NED2 Entity disambiguation (via description) batch_6a05bf8bd1cc8190a67b98eb43b4d850 completed May 14, 2026, 12:26 p.m.
Created at: April 10, 2026, 12:02 p.m.