Triple

T1311351
Position Surface form Disambiguated ID Type / Status
Subject Vanuatu E27996 entity
Predicate hasIsland P970 FINISHED
Object Tanna
Tanna is a volcanic island in southern Vanuatu known for its active Mount Yasur volcano and traditional kastom villages.
E217569 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: Tanna | Statement: [Vanuatu, hasIsland, Tanna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tanna
Context triple: [Vanuatu, hasIsland, Tanna]
  • A. Rotuma
    Rotuma is a remote volcanic island and dependency of Fiji in the South Pacific Ocean, known for its distinct Polynesian culture and language.
  • B. Vella Lavella
    Vella Lavella is an Oceanic language spoken on Vella Lavella Island in the Solomon Islands, belonging to the Meso-Melanesian branch of the Austronesian language family.
  • C. Kadavu
    Kadavu is one of Fiji's main islands, known for its rugged, unspoiled landscapes and world-class diving along the Great Astrolabe Reef.
  • D. Hiri Motu
    Hiri Motu is an Austronesian lingua franca and one of the official languages of Papua New Guinea, historically used for trade and communication among diverse ethnic groups.
  • E. Savaiʻi
    Savaiʻi is the largest and one of the main islands of Samoa, known for its volcanic landscapes, traditional villages, and relatively undeveloped, rural character.
  • 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: Tanna
Triple: [Vanuatu, hasIsland, Tanna]
Generated description
Tanna is a volcanic island in southern Vanuatu known for its active Mount Yasur volcano and traditional kastom villages.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tanna
Target entity description: Tanna is a volcanic island in southern Vanuatu known for its active Mount Yasur volcano and traditional kastom villages.
  • A. Rotuma
    Rotuma is a remote volcanic island and dependency of Fiji in the South Pacific Ocean, known for its distinct Polynesian culture and language.
  • B. Vella Lavella
    Vella Lavella is an Oceanic language spoken on Vella Lavella Island in the Solomon Islands, belonging to the Meso-Melanesian branch of the Austronesian language family.
  • C. Kadavu
    Kadavu is one of Fiji's main islands, known for its rugged, unspoiled landscapes and world-class diving along the Great Astrolabe Reef.
  • D. Hiri Motu
    Hiri Motu is an Austronesian lingua franca and one of the official languages of Papua New Guinea, historically used for trade and communication among diverse ethnic groups.
  • E. Savaiʻi
    Savaiʻi is the largest and one of the main islands of Samoa, known for its volcanic landscapes, traditional villages, and relatively undeveloped, rural character.
  • 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_69a496d7d83481908f83085854e51328 completed March 1, 2026, 7:43 p.m.
NER Named-entity recognition batch_69a4c1560f888190bdd9107b08395e0b completed March 1, 2026, 10:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69adf3ae387c8190b72ca26ab81a53b6 completed March 8, 2026, 10:09 p.m.
NEDg Description generation batch_69adf55207248190bd903c7faa3729e7 completed March 8, 2026, 10:16 p.m.
NED2 Entity disambiguation (via description) batch_69adf5e074088190b6b383fb93cd18d8 completed March 8, 2026, 10:19 p.m.
Created at: March 1, 2026, 7:51 p.m.