Triple
T26299480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buli (Halmahera) |
E661511
|
entity |
| Predicate | isSpokenOnSideOfIsland |
P44066
|
FINISHED |
| Object | eastern Halmahera |
—
|
LITERAL FINISHED |
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: eastern Halmahera | Statement: [Buli (Halmahera), isSpokenOnSideOfIsland, eastern Halmahera]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isSpokenOnSideOfIsland Context triple: [Buli (Halmahera), isSpokenOnSideOfIsland, eastern Halmahera]
-
A.
spokenOnIsland
Indicates that an act of speaking or a spoken utterance occurred while the speaker was on an island.
-
B.
isOnSideOfIsland
chosen
Indicates that one entity is located on a particular side or shore of an island relative to some reference or division.
-
C.
isSpokenInTerrain
Indicates that a particular language or speech form is used or occurs within a specific type of terrain or geographical environment.
-
D.
spokenInIslandGroup
Indicates that a language or speech variety is used or spoken within a particular group of islands.
-
E.
isSpokenOn
Indicates that a particular language, phrase, or utterance is used or occurs during a specified time, event, or occasion.
- 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_69ee812cd48c81908054068f545f0526 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f61f12b0f08190bc4a16907941864c |
completed | May 2, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69f61b3a8ae0819090189fbd8eb19f2f |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 26, 2026, 10:14 p.m.