Triple

T8010352
Position Surface form Disambiguated ID Type / Status
Subject Haʻapai E186472 entity
Predicate hasIsland P970 FINISHED
Object Tungua
Tungua is a small inhabited island in the Haʻapai group of the Kingdom of Tonga, known for its traditional Polynesian village life and surrounding coral reefs.
E709137 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: Tungua | Statement: [Haʻapai, hasIsland, Tungua]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tungua
Context triple: [Haʻapai, hasIsland, Tungua]
  • A. Tewai
    Tewai is a settlement on the atoll of Tabiteuea in the island nation of Kiribati in the central Pacific Ocean.
  • B. Tongolo
    "Tongolo" is the breakthrough Afrobeat single by Nigerian artist D'banj that helped launch his music career across Africa.
  • C. Tongelre
    Tongelre is a district in the Dutch city of Eindhoven, known for its mix of residential neighborhoods, green spaces, and former industrial areas.
  • D. Hualañé
    Hualañé is a rural Chilean town and commune in the Maule Region, known for its agricultural activities and location near the Mataquito River.
  • E. Tillangchong
    Tillangchong is a remote, sparsely inhabited island in India’s Nicobar archipelago, noted for its dense tropical forests and rich marine and bird life.
  • 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: Tungua
Triple: [Haʻapai, hasIsland, Tungua]
Generated description
Tungua is a small inhabited island in the Haʻapai group of the Kingdom of Tonga, known for its traditional Polynesian village life and surrounding coral reefs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tungua
Target entity description: Tungua is a small inhabited island in the Haʻapai group of the Kingdom of Tonga, known for its traditional Polynesian village life and surrounding coral reefs.
  • A. Tewai
    Tewai is a settlement on the atoll of Tabiteuea in the island nation of Kiribati in the central Pacific Ocean.
  • B. Tongolo
    "Tongolo" is the breakthrough Afrobeat single by Nigerian artist D'banj that helped launch his music career across Africa.
  • C. Tongelre
    Tongelre is a district in the Dutch city of Eindhoven, known for its mix of residential neighborhoods, green spaces, and former industrial areas.
  • D. Hualañé
    Hualañé is a rural Chilean town and commune in the Maule Region, known for its agricultural activities and location near the Mataquito River.
  • E. Tillangchong
    Tillangchong is a remote, sparsely inhabited island in India’s Nicobar archipelago, noted for its dense tropical forests and rich marine and bird life.
  • 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_69ca82abaffc8190ab8af79cdbc31ab3 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3d70caf8819090a9f98025470c0d completed March 31, 2026, 3:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc63c1f76881909ad6d7777090f2e2 completed April 1, 2026, 12:16 a.m.
NEDg Description generation batch_69cc651b4be08190ad76c70b1d617c1a completed April 1, 2026, 12:21 a.m.
NED2 Entity disambiguation (via description) batch_69cc664700dc819097d149931cf49673 completed April 1, 2026, 12:26 a.m.
Created at: March 30, 2026, 5:19 p.m.