Triple

T9748009
Position Surface form Disambiguated ID Type / Status
Subject Atiu E236365 entity
Predicate hasSettlement P1068 FINISHED
Object Mapumai
Mapumai is a small village settlement on the island of Atiu in the Cook Islands.
 E817643 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: Mapumai | Statement: [Atiu, hasSettlement, Mapumai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mapumai
Context triple: [Atiu, hasSettlement, Mapumai]
  • A. Mapah
    Mapah is Rabbi Moses Isserles’s glosses on the Shulchan Aruch, integrating Ashkenazi customs and rulings into that foundational Jewish legal code.
  • B. Wallmapu
    Wallmapu is the ancestral homeland of the Mapuche people, encompassing their traditional territories across parts of present-day Chile and Argentina.
  • C. Maap
    Maap is one of the islands in the Yap archipelago of the Federated States of Micronesia, known for its traditional culture and Pacific island environment.
  • D. Mapun
    Mapun is an Austronesian language spoken primarily by the Mapun people of the southern Philippines, particularly on Mapun (Cagayan de Sulu) Island in the Sulu Sea.
  • E. Maa
    Maa is a Nilotic language spoken primarily by the Maasai people of Kenya and Tanzania.
  • 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: Mapumai
Triple: [Atiu, hasSettlement, Mapumai]
Generated description
Mapumai is a small village settlement on the island of Atiu in the Cook Islands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mapumai
Target entity description: Mapumai is a small village settlement on the island of Atiu in the Cook Islands.
  • A. Mapah
    Mapah is Rabbi Moses Isserles’s glosses on the Shulchan Aruch, integrating Ashkenazi customs and rulings into that foundational Jewish legal code.
  • B. Wallmapu
    Wallmapu is the ancestral homeland of the Mapuche people, encompassing their traditional territories across parts of present-day Chile and Argentina.
  • C. Maap
    Maap is one of the islands in the Yap archipelago of the Federated States of Micronesia, known for its traditional culture and Pacific island environment.
  • D. Mapun
    Mapun is an Austronesian language spoken primarily by the Mapun people of the southern Philippines, particularly on Mapun (Cagayan de Sulu) Island in the Sulu Sea.
  • E. Maa
    Maa is a Nilotic language spoken primarily by the Maasai people of Kenya and Tanzania.
  • 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_69ca84d3e24481908a476e2231123cf9 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9f68f8b88190b44babf5ae17dfef completed April 1, 2026, 10:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1b00d76488190af68cba694dc329c completed April 5, 2026, 12:42 a.m.
NEDg Description generation batch_69d1b0f8eacc81909643c6f74e049faa completed April 5, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_69d1b153fec481909a289b14789f0a40 completed April 5, 2026, 12:48 a.m.
Created at: March 30, 2026, 8:23 p.m.