Triple
T8292791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stannary parliaments |
E193939
|
entity |
| Predicate | hadSeatIn |
P15391
|
FINISHED |
| Object | Launceston |
E486762
|
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: Launceston | Statement: [Stannary parliaments, hadSeatIn, Launceston]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Launceston Context triple: [Stannary parliaments, hadSeatIn, Launceston]
-
A.
Launceston
Launceston is a major city in northern Tasmania, Australia, known for its historic architecture, Cataract Gorge, and role as a regional commercial and cultural hub.
-
B.
Launceston
chosen
Launceston is a historic market town in eastern Cornwall, England, known for its medieval castle and role as a former county town.
-
C.
Hobart
Hobart is the capital city of the Australian island state of Tasmania, known for its historic waterfront, proximity to Mount Wellington, and vibrant arts and food scenes.
-
D.
Port Vincent
Port Vincent is a coastal township and holiday destination on South Australia's Yorke Peninsula, known for its sheltered bay, marina, and recreational fishing and boating.
-
E.
Fremantle
Fremantle is a global television production and distribution company known for creating and producing major entertainment formats and reality shows.
- 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_69ca82e32db481908b72f3804fa71152 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7c9deb50819086ae9c97b03fefc3 |
completed | March 31, 2026, 7:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd6899b818819090c80a8eba7d5d4c |
completed | April 1, 2026, 6:48 p.m. |
Created at: March 30, 2026, 5:52 p.m.