Triple
T4494521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bismarck Sea |
E100660
|
entity |
| Predicate | hasNearbyIsland |
P970
|
FINISHED |
| Object | New Britain |
E78913
|
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: New Britain | Statement: [Bismarck Sea, hasNearbyIsland, New Britain]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: New Britain Context triple: [Bismarck Sea, hasNearbyIsland, New Britain]
-
A.
New Britain
chosen
New Britain is a large volcanic island in the Bismarck Archipelago of Papua New Guinea, known for its rugged terrain, active volcanoes, and diverse indigenous cultures.
-
B.
New Britain
New Britain is a mid-sized industrial city in central Connecticut known historically for its manufacturing and hardware industries.
-
C.
Lou Island
Lou Island is one of the islands in the Admiralty Islands group of Papua New Guinea, located in the southwestern Pacific Ocean.
-
D.
Freeport
Freeport is a major Bahamian city on Grand Bahama known as a free-trade zone and popular tourist and commercial hub.
-
E.
Freeport
Freeport is a waterfront village on Long Island in New York known for its marinas, fishing industry, and nautical tourism.
- 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_69bd43cdf15081909a4fa2585ff63b3e |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5572c60881909101b4e65dd5de06 |
completed | March 20, 2026, 2:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bd6f8190e88190aec651ac9fe9ef92 |
completed | March 20, 2026, 4:02 p.m. |
Created at: March 20, 2026, 1 p.m.