Triple

T6511954
Position Surface form Disambiguated ID Type / Status
Subject Gambier Islands E150157 entity
Predicate hasIsland P970 FINISHED
Object Makaroa
Makaroa is one of the smaller, remote islands in the Gambier Islands archipelago of French Polynesia in the South Pacific Ocean.
 E601958 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: Makaroa | Statement: [Gambier Islands, hasIsland, Makaroa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Makaroa
Context triple: [Gambier Islands, hasIsland, Makaroa]
  • A. Orongo
    Orongo is a ceremonial stone village and archaeological site on Easter Island, best known for its role in the Birdman cult and its dramatic clifftop setting overlooking the ocean.
  • B. Waharoa
    Waharoa is a small rural township in the Waikato region of New Zealand, located near Matamata and serving as a local service and transport hub for the surrounding farming community.
  • C. Coelemu
    Coelemu is a town and commune in Chile’s Ñuble Region, located near the Pacific coast in the Itata River valley.
  • D. Tupuri
    The Tupuri are an ethnic group of Central Africa, primarily living in northern Cameroon and southwestern Chad, known for their distinct language and agrarian lifestyle.
  • E. Maoka
    Maoka is the former Japanese name of the port town now known as Kholmsk on Russia’s Sakhalin Island.
  • 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: Makaroa
Triple: [Gambier Islands, hasIsland, Makaroa]
Generated description
Makaroa is one of the smaller, remote islands in the Gambier Islands archipelago of French Polynesia in the South Pacific Ocean.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Makaroa
Target entity description: Makaroa is one of the smaller, remote islands in the Gambier Islands archipelago of French Polynesia in the South Pacific Ocean.
  • A. Orongo
    Orongo is a ceremonial stone village and archaeological site on Easter Island, best known for its role in the Birdman cult and its dramatic clifftop setting overlooking the ocean.
  • B. Waharoa
    Waharoa is a small rural township in the Waikato region of New Zealand, located near Matamata and serving as a local service and transport hub for the surrounding farming community.
  • C. Coelemu
    Coelemu is a town and commune in Chile’s Ñuble Region, located near the Pacific coast in the Itata River valley.
  • D. Tupuri
    The Tupuri are an ethnic group of Central Africa, primarily living in northern Cameroon and southwestern Chad, known for their distinct language and agrarian lifestyle.
  • E. Maoka
    Maoka is the former Japanese name of the port town now known as Kholmsk on Russia’s Sakhalin Island.
  • 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_69c687ef291081909d437f035eef1cda completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c69f3c5eb88190a56723acd8096dd8 completed March 27, 2026, 3:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6cb6421748190b8f2b77c77b153bc completed March 27, 2026, 6:24 p.m.
NEDg Description generation batch_69c6cd049fac81908c955caa0ccac5ba completed March 27, 2026, 6:31 p.m.
NED2 Entity disambiguation (via description) batch_69c6ce00096c8190a3015bcd392e0ce4 completed March 27, 2026, 6:35 p.m.
Created at: March 27, 2026, 1:44 p.m.