Triple

T9349028
Position Surface form Disambiguated ID Type / Status
Subject Taha'a E224967 entity
Predicate hasMainSettlement P2106 FINISHED
Object Haamene
Haamene is the principal village and administrative center on the island of Taha'a in French Polynesia.
 E792518 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: Haamene | Statement: [Taha'a, hasMainSettlement, Haamene]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Haamene
Context triple: [Taha'a, hasMainSettlement, Haamene]
  • A. Hemulen
    Hemulen is a character from Tove Jansson’s Moomin series, typically portrayed as a tall, earnest, and somewhat pedantic creature obsessed with hobbies like stamp collecting and botany.
  • B. Poulus
    Poulus is a personal name variant derived from the given name Poul.
  • C. Haukeli
    Haukeli is a mountainous village area in southern Norway known as a key transit point and outdoor recreation destination, especially for skiing and hiking.
  • D. Hannut
    Hannut is a municipality in the French-speaking Walloon Region of Belgium, known for its rural character and location between Liège and Brussels.
  • E. Donder
    Donder is one of Santa Claus’s traditional reindeer, often listed alongside Dancer and the other members of his Christmas sleigh team.
  • 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: Haamene
Triple: [Taha'a, hasMainSettlement, Haamene]
Generated description
Haamene is the principal village and administrative center on the island of Taha'a in French Polynesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Haamene
Target entity description: Haamene is the principal village and administrative center on the island of Taha'a in French Polynesia.
  • A. Hemulen
    Hemulen is a character from Tove Jansson’s Moomin series, typically portrayed as a tall, earnest, and somewhat pedantic creature obsessed with hobbies like stamp collecting and botany.
  • B. Poulus
    Poulus is a personal name variant derived from the given name Poul.
  • C. Haukeli
    Haukeli is a mountainous village area in southern Norway known as a key transit point and outdoor recreation destination, especially for skiing and hiking.
  • D. Hannut
    Hannut is a municipality in the French-speaking Walloon Region of Belgium, known for its rural character and location between Liège and Brussels.
  • E. Donder
    Donder is one of Santa Claus’s traditional reindeer, often listed alongside Dancer and the other members of his Christmas sleigh team.
  • 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_69ca842993248190a79ab06968994b86 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd4f1198b88190adc0b01f7c1be36e completed April 1, 2026, 5 p.m.
NED1 Entity disambiguation (via context triple) batch_69d0e43c31008190b542a9c5aa33f30e completed April 4, 2026, 10:13 a.m.
NEDg Description generation batch_69d0e587586c8190a73ce417f0b5adec completed April 4, 2026, 10:18 a.m.
NED2 Entity disambiguation (via description) batch_69d0e5eb2ce88190973acc2cc8ce254f completed April 4, 2026, 10:20 a.m.
Created at: March 30, 2026, 7:41 p.m.