Triple
T26621891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mauga Mu |
E668221
|
entity |
| Predicate | onIslandGroup |
P40757
|
FINISHED |
| Object | Samoan Islands |
—
|
NE NERFINISHED |
How this triple was built (2 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: Samoan Islands | Statement: [Mauga Mu, onIslandGroup, Samoan Islands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onIslandGroup Context triple: [Mauga Mu, onIslandGroup, Samoan Islands]
-
A.
isInIslandGroup
chosen
Indicates that one geographic entity (typically an island) is located within or belongs to a specific island group or archipelago.
-
B.
hasIslandGroupType
Indicates that an island group is classified as having a particular type or category of island grouping.
-
C.
coversIslandGroup
Indicates that one geographic entity extends over, includes, or encompasses an entire group of islands.
-
D.
associatedWithIslandGroup
Indicates that something has a connection or relationship to a particular group of islands, such as belonging to, being part of, or being relevant to that island group.
-
E.
hasIslandGroupOnOneSide
Indicates that one side or boundary of an entity is adjacent or oriented toward a particular island group.
- F. None of above.
Provenance (3 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_69ee9cff507c819092b95bf7219a702e |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f615e69e708190af8093e2014052b1 |
completed | May 2, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69f60b8bb0d08190ab5a9a2a8847c6f4 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 2:21 a.m.