Triple
T16442867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Austrasia |
E399347
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Verdun |
E69406
|
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: Verdun | Statement: [Austrasia, capital, Verdun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Verdun Context triple: [Austrasia, capital, Verdun]
-
A.
Verdun
Verdun is a tram stop on the Tramway de Tours network in the city of Tours, France.
-
B.
Verdun
Verdun is a borough of Montreal, Quebec, known for its historic waterfront along the St. Lawrence River and its mix of residential neighborhoods and urban amenities.
-
C.
Battle of Verdun
The Battle of Verdun was one of the longest and bloodiest engagements of World War I, symbolizing the brutal attrition warfare on the Western Front between France and Germany in 1916.
-
D.
Verdun, France
chosen
Verdun, France is a historic northeastern French city on the Meuse River, best known as the site of one of World War I’s largest and bloodiest battles.
-
E.
Battle of La Bassée
The Battle of La Bassée was a World War I engagement on the Western Front in 1914, fought between British and German forces in northern France as part of the early "Race to the Sea" operations.
- 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_69d87f2c6778819080fcfae53be8f12a |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32cd8d2988190acb5722a15623319 |
completed | April 18, 2026, 7:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00458f8f3c8190ad5eff2ad2a32dea |
completed | May 10, 2026, 8:45 a.m. |
Created at: April 10, 2026, 5:10 a.m.