Triple
T1302639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central Malayo-Polynesian languages |
E27800
|
entity |
| Predicate | spokenIn |
P2266
|
FINISHED |
| Object |
Alor archipelago
The Alor archipelago is a group of remote islands in eastern Indonesia known for its linguistic diversity, including many Central Malayo-Polynesian and Papuan languages, and rich marine biodiversity.
|
E210291
|
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: Alor archipelago | Statement: [Central Malayo-Polynesian languages, spokenIn, Alor archipelago]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alor archipelago Context triple: [Central Malayo-Polynesian languages, spokenIn, Alor archipelago]
-
A.
Nggela Islands
The Nggela Islands, also known as the Florida Islands, are a small group of islands in the Central Province of the Solomon Islands, noted for their role in World War II and their rich marine and coastal ecosystems.
-
B.
Kangean Islands
The Kangean Islands are a remote Indonesian archipelago in the Java Sea, northeast of Madura, known for their predominantly Madurese culture and traditional maritime livelihoods.
-
C.
Sulu Archipelago
The Sulu Archipelago is a chain of islands in the southwestern Philippines, known for its strategic location between Mindanao and Borneo and its culturally distinct, predominantly Muslim communities.
-
D.
Banda Islands
The Banda Islands are a remote Indonesian archipelago in the Maluku province, historically renowned as the world’s original source of nutmeg and a focal point of European colonial spice trade.
-
E.
Ssese Islands
The Ssese Islands are an archipelago of lush, tropical islands in Uganda known for their scenic beaches, biodiversity, and growing eco-tourism on Lake Victoria.
- 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: Alor archipelago Triple: [Central Malayo-Polynesian languages, spokenIn, Alor archipelago]
Generated description
The Alor archipelago is a group of remote islands in eastern Indonesia known for its linguistic diversity, including many Central Malayo-Polynesian and Papuan languages, and rich marine biodiversity.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Alor archipelago Target entity description: The Alor archipelago is a group of remote islands in eastern Indonesia known for its linguistic diversity, including many Central Malayo-Polynesian and Papuan languages, and rich marine biodiversity.
-
A.
Nggela Islands
The Nggela Islands, also known as the Florida Islands, are a small group of islands in the Central Province of the Solomon Islands, noted for their role in World War II and their rich marine and coastal ecosystems.
-
B.
Kangean Islands
The Kangean Islands are a remote Indonesian archipelago in the Java Sea, northeast of Madura, known for their predominantly Madurese culture and traditional maritime livelihoods.
-
C.
Sulu Archipelago
The Sulu Archipelago is a chain of islands in the southwestern Philippines, known for its strategic location between Mindanao and Borneo and its culturally distinct, predominantly Muslim communities.
-
D.
Banda Islands
The Banda Islands are a remote Indonesian archipelago in the Maluku province, historically renowned as the world’s original source of nutmeg and a focal point of European colonial spice trade.
-
E.
Ssese Islands
The Ssese Islands are an archipelago of lush, tropical islands in Uganda known for their scenic beaches, biodiversity, and growing eco-tourism on Lake Victoria.
- 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_69a4c115ba64819081c55fa6807e19ef |
completed | March 1, 2026, 10:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69addf2374ac8190ac2a2a753c056a3d |
completed | March 8, 2026, 8:42 p.m. |
| NEDg | Description generation | batch_69ade16fdfdc81908299c6bf1fd973d8 |
completed | March 8, 2026, 8:52 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ade1b832fc81908bd9ab364cd333c7 |
completed | March 8, 2026, 8:53 p.m. |
Created at: March 1, 2026, 7:51 p.m.