Triple
T25345082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orango |
E635522
|
entity |
| Predicate | principalIslandOf |
P29204
|
FINISHED |
| Object | Bijagós Archipelago |
—
|
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: Bijagós Archipelago | Statement: [Orango, principalIslandOf, Bijagós Archipelago]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: principalIslandOf Context triple: [Orango, principalIslandOf, Bijagós Archipelago]
-
A.
islandOf
chosen
Indicates that one place is an island belonging to, located within, or geographically associated with another specified area or body of land/water.
-
B.
nearestPopulatedIsland
Indicates that one island is the closest populated island to another specified location or island.
-
C.
formerIslandOf
Indicates that one entity was previously an island associated with another entity, but no longer holds that status.
-
D.
capitalOfIsland
Indicates that a location serves as the capital city or administrative center of a specified island.
-
E.
largestIslandOfCountry
Indicates that one entity is the largest island (by area) belonging to or within the territory of the specified country.
- 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_69e75a9ac5d881909387ed766e20cd47 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f498bb04ec8190bd125654fdcd2027 |
completed | May 1, 2026, 12:12 p.m. |
| PD | Predicate disambiguation | batch_69f4806d93dc8190b9dff4c63186faff |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 1:34 p.m.