Triple
T16783138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | World War I battlefields |
E407904
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Verdun battlefield |
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 battlefield | Statement: [World War I battlefields, hasPart, Verdun battlefield]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Verdun battlefield Context triple: [World War I battlefields, hasPart, Verdun battlefield]
-
A.
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.
-
B.
Verdun
Verdun is a tram stop on the Tramway de Tours network in the city of Tours, France.
-
C.
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.
-
D.
Ligny battlefield
Ligny battlefield is the historic site in present-day Belgium where Napoleon achieved his last victory in 1815, two days before his final defeat at Waterloo.
-
E.
Gravelotte
Gravelotte is a village in northeastern France best known as the site of a major 1870 Franco-Prussian War battle.
- 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_69d8839270588190886720d9519bbf8f |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3b218d31881908d896e688ebd171c |
completed | April 18, 2026, 4:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00b287a96c8190a16d7c76d05be106 |
completed | May 10, 2026, 4:29 p.m. |
Created at: April 10, 2026, 5:22 a.m.