Triple

T9775813
Position Surface form Disambiguated ID Type / Status
Subject Ngāpuhi E237243 entity
Predicate hasWaka P90582 FINISHED
Object Māmari
Māmari is a traditional Māori voyaging canoe (waka) associated with the Ngāpuhi iwi, significant in their ancestral migration and tribal identity.
 E820123 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: Māmari | Statement: [Ngāpuhi, hasWaka, Māmari]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Māmari
Context triple: [Ngāpuhi, hasWaka, Māmari]
  • A. Mamati
    Mamati is a village in western Georgia notable as the birthplace of former Soviet and Georgian politician Eduard Shevardnadze.
  • B. Mawanella
    Mawanella is a town in central Sri Lanka known as a key transit point on the Colombo–Kandy road and for its surrounding rubber and tea plantations.
  • C. Marau
    Marau is an Oceanic language spoken by a small community in Papua New Guinea.
  • D. Moukari
    Moukari is a Finnish amateur radio callsign holder, identified by the callsign K9FIN Moukari.
  • E. Mawé
    Mawé is an indigenous Tupian language spoken by the Sateré-Mawé people of the Brazilian Amazon.
  • 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: Māmari
Triple: [Ngāpuhi, hasWaka, Māmari]
Generated description
Māmari is a traditional Māori voyaging canoe (waka) associated with the Ngāpuhi iwi, significant in their ancestral migration and tribal identity.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Māmari
Target entity description: Māmari is a traditional Māori voyaging canoe (waka) associated with the Ngāpuhi iwi, significant in their ancestral migration and tribal identity.
  • A. Mamati
    Mamati is a village in western Georgia notable as the birthplace of former Soviet and Georgian politician Eduard Shevardnadze.
  • B. Mawanella
    Mawanella is a town in central Sri Lanka known as a key transit point on the Colombo–Kandy road and for its surrounding rubber and tea plantations.
  • C. Marau
    Marau is an Oceanic language spoken by a small community in Papua New Guinea.
  • D. Moukari
    Moukari is a Finnish amateur radio callsign holder, identified by the callsign K9FIN Moukari.
  • E. Mawé
    Mawé is an indigenous Tupian language spoken by the Sateré-Mawé people of the Brazilian Amazon.
  • 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_69ca84d975a08190aab25b02a89bdab3 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda1325a988190a07a3dc4dce41cb3 completed April 1, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1bd1d4b6881908b773e03de17f680 completed April 5, 2026, 1:38 a.m.
NEDg Description generation batch_69d1be7f967081909be670dd9e376aa5 completed April 5, 2026, 1:44 a.m.
NED2 Entity disambiguation (via description) batch_69d1bee593508190ab647ebc96a3f91e completed April 5, 2026, 1:46 a.m.
Created at: March 30, 2026, 8:26 p.m.