Triple
T9382839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pohnpei International Airport |
E225827
|
entity |
| Predicate | cityServed |
P82
|
FINISHED |
| Object | Kolonia |
E225824
|
NE 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: Kolonia | Statement: [Pohnpei International Airport, cityServed, Kolonia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kolonia Context triple: [Pohnpei International Airport, cityServed, Kolonia]
-
A.
Kolonia
chosen
Kolonia is the main urban center and former administrative hub on the island of Pohnpei in the Federated States of Micronesia.
-
B.
Colonia
Colonia is the main administrative and population center of Yap State in the Federated States of Micronesia, located on the island of Yap.
-
C.
Colonia
Colonia is the historical Latin name for the German city of Cologne, reflecting its origins as a Roman colony.
-
D.
Colonarie
Colonarie is a small village in Saint Vincent and the Grenadines, known as the birthplace of Prime Minister Ralph Gonsalves.
-
E.
Colonet
Colonet is a rural community in the municipality of Ensenada in Baja California, Mexico, known for its agricultural activity and proposed deep-water port development.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca842e9dcc8190a264119e683cfe04 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd50c11d648190b03cedbce0b72c60 |
completed | April 1, 2026, 5:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d100ddec0c8190854fb5db36e840db |
completed | April 4, 2026, 12:15 p.m. |
Created at: March 30, 2026, 7:44 p.m.