Triple
T12647000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruahine Range |
E302050
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Dannevirke |
E290329
|
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: Dannevirke | Statement: [Ruahine Range, nearbySettlement, Dannevirke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dannevirke Context triple: [Ruahine Range, nearbySettlement, Dannevirke]
-
A.
Dannevirke
chosen
Dannevirke is a rural service town in New Zealand known for its Scandinavian heritage and farming-based economy.
-
B.
Wraeclast
Wraeclast is a dark, cursed continent that serves as the primary game world in the action role-playing game Path of Exile.
-
C.
Braavos
Braavos is a powerful, canal-filled free city in the world of "A Song of Ice and Fire" and "Game of Thrones," famed for its secretive Iron Bank, skilled assassins of the Faceless Men, and strong naval might.
-
D.
Westerland
Westerland is the main town and a popular seaside resort on the North Sea island of Sylt in Germany.
-
E.
Watervale
Watervale is a small South Australian town renowned for its high-quality Riesling wines within the Clare Valley wine region.
- 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_69d7bdec9f9c8190b4bac675b7588211 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9614cefdc81908cfc4a4d04aa6eda |
completed | April 10, 2026, 8:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6687bbb408190b80da2d0310f82c5 |
completed | May 2, 2026, 9:11 p.m. |
Created at: April 9, 2026, 5:17 p.m.