Triple
T15208212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lomaiviti group |
E363444
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object |
Koro
Koro is a volcanic island in Fiji’s Lomaiviti archipelago, known for its rugged terrain, traditional villages, and surrounding coral reefs.
|
E1143115
|
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: Koro | Statement: [Lomaiviti group, hasIsland, Koro]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Koro Context triple: [Lomaiviti group, hasIsland, Koro]
-
A.
Koro Uma
Koro Uma is an alternate name for the Uma language, an Austronesian language spoken in Central Sulawesi, Indonesia.
-
B.
Koro Wachi
Koro Wachi is a lesser-known Plateau language spoken in central Nigeria, notable for its place within the Benue–Congo branch of the Niger–Congo language family.
-
C.
Kogarah
Kogarah is a suburb in southern Sydney, New South Wales, Australia, known as a residential and commercial hub in the St George area.
-
D.
Rakau
Rakau is a small rural settlement in Belarus located near the historical hill of Dziaržynskaja Hara, the country’s highest point.
-
E.
Kameari
Kameari is a neighborhood in Tokyo best known as the long-running setting of the manga and anime series "Kochira Katsushika-ku Kameari Kōen-mae Hashutsujo" ("Kochikame").
- 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: Koro Triple: [Lomaiviti group, hasIsland, Koro]
Generated description
Koro is a volcanic island in Fiji’s Lomaiviti archipelago, known for its rugged terrain, traditional villages, and surrounding coral reefs.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Koro Target entity description: Koro is a volcanic island in Fiji’s Lomaiviti archipelago, known for its rugged terrain, traditional villages, and surrounding coral reefs.
-
A.
Koro Uma
Koro Uma is an alternate name for the Uma language, an Austronesian language spoken in Central Sulawesi, Indonesia.
-
B.
Koro Wachi
Koro Wachi is a lesser-known Plateau language spoken in central Nigeria, notable for its place within the Benue–Congo branch of the Niger–Congo language family.
-
C.
Kogarah
Kogarah is a suburb in southern Sydney, New South Wales, Australia, known as a residential and commercial hub in the St George area.
-
D.
Rakau
Rakau is a small rural settlement in Belarus located near the historical hill of Dziaržynskaja Hara, the country’s highest point.
-
E.
Kameari
Kameari is a neighborhood in Tokyo best known as the long-running setting of the manga and anime series "Kochira Katsushika-ku Kameari Kōen-mae Hashutsujo" ("Kochikame").
- 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_69d85a0b78bc8190b6e5ad51a2c4cfc5 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e006b8e2788190bd1831762e4181ae |
completed | April 15, 2026, 9:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fed33dbda08190a10ba81082d0d183 |
completed | May 9, 2026, 6:25 a.m. |
| NEDg | Description generation | batch_69fed47c88d08190a4396b955c9bb388 |
completed | May 9, 2026, 6:30 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fed50956408190b1426d578803974e |
completed | May 9, 2026, 6:32 a.m. |
Created at: April 10, 2026, 3:11 a.m.