Triple

T6564701
Position Surface form Disambiguated ID Type / Status
Subject Lakon E153873 entity
Predicate spokenIn P2266 FINISHED
Object Gaua
Gaua is an island in northern Vanuatu, known for its active volcano, Lake Letas, and diverse indigenous languages and cultures.
E619059 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: Gaua | Statement: [Lakon, spokenIn, Gaua]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gaua
Context triple: [Lakon, spokenIn, Gaua]
  • A. Manuae
    Manuae is an uninhabited coral atoll in the southern Cook Islands, known for its rich marine life and status as a wildlife sanctuary.
  • B. Manuae
    Manuae is a small, uninhabited coral atoll in the Society Islands of French Polynesia, known for its remote lagoon and rich marine life.
  • C. 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.
  • D. Abaiang
    Abaiang is a coral atoll in the Gilbert Islands of Kiribati, known for its traditional villages, lagoon environment, and vulnerability to climate change and sea-level rise.
  • E. Vavaʻu
    Vavaʻu is a scenic island group in northern Tonga known for its sheltered harbors, sailing, and whale-watching opportunities.
  • 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: Gaua
Triple: [Lakon, spokenIn, Gaua]
Generated description
Gaua is an island in northern Vanuatu, known for its active volcano, Lake Letas, and diverse indigenous languages and cultures.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gaua
Target entity description: Gaua is an island in northern Vanuatu, known for its active volcano, Lake Letas, and diverse indigenous languages and cultures.
  • A. Manuae
    Manuae is an uninhabited coral atoll in the southern Cook Islands, known for its rich marine life and status as a wildlife sanctuary.
  • B. Manuae
    Manuae is a small, uninhabited coral atoll in the Society Islands of French Polynesia, known for its remote lagoon and rich marine life.
  • C. 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.
  • D. Abaiang
    Abaiang is a coral atoll in the Gilbert Islands of Kiribati, known for its traditional villages, lagoon environment, and vulnerability to climate change and sea-level rise.
  • E. Vavaʻu
    Vavaʻu is a scenic island group in northern Tonga known for its sheltered harbors, sailing, and whale-watching opportunities.
  • 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_69c6880cb35881909b763eb0125236b9 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ae3b9ec8819080f3052556d95810 completed March 27, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c71a5fb5f88190942a67cb38378964 completed March 28, 2026, 12:01 a.m.
NEDg Description generation batch_69c71b5a3550819085d7030a83249e78 completed March 28, 2026, 12:05 a.m.
NED2 Entity disambiguation (via description) batch_69c71ba93da88190a5e4022ebb8e3256 completed March 28, 2026, 12:07 a.m.
Created at: March 27, 2026, 1:52 p.m.